SlideShare a Scribd company logo

M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020)

A
ALINLAB

Jaehyung Kim*, Jongheon Jeong*, Jinwoo Shin arXiv: https://arxiv.org/abs/2004.00431 code: https://github.com/alinlab/M2m

1 of 10
Download to read offline
M2m: Imbalanced Classification via
Major-to-minor Translation
Jaehyung Kim* Jongheon Jeong* Jinwoo Shin
*Equal contribution
Korea Advanced Institute of Science and Technology (KAIST)
• Many real-world datasets have imbalanced class distributions
• Standard training (e.g. ERM) often fails to generalize at the “tail” classes
[Wang et al. 2017; Cui et al. 2019; Cao et al. 2019]
Class Imbalance in Training Data
Species [Van Horn et al. 2019] Places [Wang et al. 2017]
[Wang et al. 2017] Learning to Model the Tail. NeurIPS, 2017
[Van Horn et al. 2019] The iNaturalist Species Classification and Detection Dataset. In CVPR, 2018
[Cao et al. 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. In NeurIPS 2019
[Cui et al. 2019] Class-balanced Loss Based on Effective Number of Samples. In CVPR, 2019
• Many real-world datasets have imbalanced class distributions
• Standard training (e.g. ERM) often fails to generalize at the “tail” classes
[Wang et al. 2017; Cui et al. 2019; Cao et al. 2019]
• Several training strategies have been investigated
Class Imbalance in Training Data
Re-balancing methods
• Re-sampling
[Japkowicz et al. 2000; Chawla et al. 2002]
• Re-weighting
[Khan et al. 2017; Cui et al. 2019]
Regularization methods
• Margin-based method
[Dong et al. 2017; Cao et al. 2019]
• Minority focused loss
[Lin et al. 2017]
Fundamental problem: Limited information of minority classes
[Japkowicz et al. 2000] The Class Imbalance Problem: Significance and Strategies. In ICAI 2000
[Chawla et al. 2002] SMOTE: Synthetic Minority Oversampling Technique. In JAIR 2002
[Khan et al. 2017] Cost-sensitive Learning of Deep Feature Representations from Imbalanced Data. In TNNLS 2017
[Dong et al. 2018] Imbalanced Deep Learning by Minority Class Incremental Rectification., TPAMI 2018
[Lin et al. 2017] Focal Loss for Dense Object Detection., CVPR 2017
• M2m augments minority classes using information of majority samples
• Over-fitting on minority classes is prevented by utilizing the diversity of majority
• A simple optimization using a pre-trained classifier surprisingly works well
M2m: Major-to-minor Translation
• M2m augments minority classes via translating from majority samples
• Each translation is done by solving the following optimization:
M2m: Major-to-minor Translation
Optimization objective of M2m
(a) Translation to minority class
- Using a pre-trained classifier
(b) Regularization for reducing a risk as majority class
- On the logit of training classifier
is used as a minority sample for training f<latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit><latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit><latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit><latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit>
x⇤
<latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">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</latexit><latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">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</latexit><latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">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</latexit><latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">AAACyHicjVHLSsNAFD2Nr1pfVZdugkUQFyWRgi4LbsRVBdMWapVkOq1D8yKZqKV04w+41S8T/0D/wjtjCmoRnZDkzLn3nJl7rxf7IpWW9Vow5uYXFpeKy6WV1bX1jfLmVjONsoRxh0V+lLQ9N+W+CLkjhfR5O064G3g+b3nDExVv3fIkFVF4IUcx7wbuIBR9wVxJlHN/NT6YXJcrVtXSy5wFdg4qyFcjKr/gEj1EYMgQgCOEJOzDRUpPBzYsxMR1MSYuISR0nGOCEmkzyuKU4RI7pO+Adp2cDWmvPFOtZnSKT29CShN7pIkoLyGsTjN1PNPOiv3Ne6w91d1G9Pdyr4BYiRti/9JNM/+rU7VI9HGsaxBUU6wZVR3LXTLdFXVz80tVkhxi4hTuUTwhzLRy2mdTa1Jdu+qtq+NvOlOxas/y3Azv6pY0YPvnOGdB87BqW1X7vFap1/JRF7GDXezTPI9QxykacMhb4BFPeDbOjNi4M0afqUYh12zj2zIePgCSSJEX</latexit>
k<latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit><latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit><latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit><latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit>
k0<latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit><latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit><latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit><latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit>
• Rejection criterion: selective use of translated sample
• This reduces a risk of unreliable generation when is small
• Optimal sampling : better choice of majority seed
• Majority classes to sample are selected by considering two aspects:
(a) Maximizes the acceptance probability (b) Chooses diverse classes
M2m: Techniques for Better Efficiency
x⇤
<latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit><latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit><latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit><latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit>
x0<latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit><latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit><latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit><latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit>
# samples of class
Nk0<latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">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</latexit><latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">AAACynicjVHLSsNAFD2Nr1pfVZdugkVwVRIR7LLgxoVIBfuAWkoyndaheTGZCKV05w+41Q8T/0D/wjtjCmoRnZDkzLnn3Jl7r58EIlWO81qwlpZXVteK66WNza3tnfLuXiuNM8l4k8VBLDu+l/JARLyphAp4J5HcC/2At/3xuY6377lMRRzdqEnCe6E3isRQME8R1b7qT8d9Z9YvV5yqY5a9CNwcVJCvRlx+wS0GiMGQIQRHBEU4gIeUni5cOEiI62FKnCQkTJxjhhJ5M1JxUnjEjuk7ol03ZyPa65ypcTM6JaBXktPGEXli0knC+jTbxDOTWbO/5Z6anPpuE/r7ea6QWIU7Yv/yzZX/9elaFIaomRoE1ZQYRlfH8iyZ6Yq+uf2lKkUZEuI0HlBcEmbGOe+zbTypqV331jPxN6PUrN6zXJvhXd+SBuz+HOciaJ1UXafqXp9W6rV81EUc4BDHNM8z1HGBBpqmykc84dm6tKQ1saafUquQe/bxbVkPH298kdY=</latexit><latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">AAACynicjVHLSsNAFD2Nr1pfVZdugkVwVRIR7LLgxoVIBfuAWkoyndaheTGZCKV05w+41Q8T/0D/wjtjCmoRnZDkzLnn3Jl7r58EIlWO81qwlpZXVteK66WNza3tnfLuXiuNM8l4k8VBLDu+l/JARLyphAp4J5HcC/2At/3xuY6377lMRRzdqEnCe6E3isRQME8R1b7qT8d9Z9YvV5yqY5a9CNwcVJCvRlx+wS0GiMGQIQRHBEU4gIeUni5cOEiI62FKnCQkTJxjhhJ5M1JxUnjEjuk7ol03ZyPa65ypcTM6JaBXktPGEXli0knC+jTbxDOTWbO/5Z6anPpuE/r7ea6QWIU7Yv/yzZX/9elaFIaomRoE1ZQYRlfH8iyZ6Yq+uf2lKkUZEuI0HlBcEmbGOe+zbTypqV331jPxN6PUrN6zXJvhXd+SBuz+HOciaJ1UXafqXp9W6rV81EUc4BDHNM8z1HGBBpqmykc84dm6tKQ1saafUquQe/bxbVkPH298kdY=</latexit><latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">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</latexit>
major minor
Q(k0|k) / 1 (Nk0
Nk)+
<latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">AAAC8nicjVHLSsNAFD3G97vq0s1gESrSkoioS8GNq1LBqmA1JHHUkDQTJhOh1H6FO3fi1h9wqx8h/oH+hXfGCD4QnZDkzLn3nJl7r5/GYaZs+7nP6h8YHBoeGR0bn5icmi7NzO5lIpcBbwYiFvLA9zIehwlvqlDF/CCV3Gv7Md/3oy0d37/gMgtFsqs6KT9qe2dJeBoGniLKLVV3KpFrX7JoibVSKVIlmMOqrOVz5R13K3W3S+Fete5GS8fLPbdUtmu2WewncApQRrEaovSEFk4gECBHGxwJFOEYHjJ6DuHARkrcEbrESUKhiXP0MEbanLI4ZXjERvQ9o91hwSa0156ZUQd0SkyvJCXDImkE5UnC+jRm4rlx1uxv3l3jqe/Wob9feLWJVTgn9i/dR+Z/dboWhVNsmBpCqik1jK4uKFxy0xV9c/apKkUOKXEan1BcEg6M8qPPzGgyU7vurWfiLyZTs3ofFLk5XvUtacDO93H+BHsrNceuOTur5c21YtQjmMcCKjTPdWxiGw00yfsK93jAo6Wsa+vGun1PtfoKzRy+LOvuDS/0n28=</latexit><latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">AAAC8nicjVHLSsNAFD3G97vq0s1gESrSkoioS8GNq1LBqmA1JHHUkDQTJhOh1H6FO3fi1h9wqx8h/oH+hXfGCD4QnZDkzLn3nJl7r5/GYaZs+7nP6h8YHBoeGR0bn5icmi7NzO5lIpcBbwYiFvLA9zIehwlvqlDF/CCV3Gv7Md/3oy0d37/gMgtFsqs6KT9qe2dJeBoGniLKLVV3KpFrX7JoibVSKVIlmMOqrOVz5R13K3W3S+Fete5GS8fLPbdUtmu2WewncApQRrEaovSEFk4gECBHGxwJFOEYHjJ6DuHARkrcEbrESUKhiXP0MEbanLI4ZXjERvQ9o91hwSa0156ZUQd0SkyvJCXDImkE5UnC+jRm4rlx1uxv3l3jqe/Wob9feLWJVTgn9i/dR+Z/dboWhVNsmBpCqik1jK4uKFxy0xV9c/apKkUOKXEan1BcEg6M8qPPzGgyU7vurWfiLyZTs3ofFLk5XvUtacDO93H+BHsrNceuOTur5c21YtQjmMcCKjTPdWxiGw00yfsK93jAo6Wsa+vGun1PtfoKzRy+LOvuDS/0n28=</latexit><latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">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</latexit><latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">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</latexit>
Q(k0|k)<latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit><latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit><latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit><latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit>

Recommended

PR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesPR-203: Class-Balanced Loss Based on Effective Number of Samples
PR-203: Class-Balanced Loss Based on Effective Number of SamplesSunghoon Joo
 
제 17회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [중고책나라] : 실시간 데이터를 이용한 Elasticsearch 클러스터 최적화
제 17회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [중고책나라] : 실시간 데이터를 이용한 Elasticsearch 클러스터 최적화제 17회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [중고책나라] : 실시간 데이터를 이용한 Elasticsearch 클러스터 최적화
제 17회 보아즈(BOAZ) 빅데이터 컨퍼런스 - [중고책나라] : 실시간 데이터를 이용한 Elasticsearch 클러스터 최적화BOAZ Bigdata
 
YJTC18 D-4 AnnexML: 近似最近傍検索を⽤いたextreme multi-label分類の⾼速化
YJTC18 D-4 AnnexML: 近似最近傍検索を⽤いたextreme multi-label分類の⾼速化YJTC18 D-4 AnnexML: 近似最近傍検索を⽤いたextreme multi-label分類の⾼速化
YJTC18 D-4 AnnexML: 近似最近傍検索を⽤いたextreme multi-label分類の⾼速化Yahoo!デベロッパーネットワーク
 
From Zero to Spring Boot Hero with GitHub Codespaces
From Zero to Spring Boot Hero with GitHub CodespacesFrom Zero to Spring Boot Hero with GitHub Codespaces
From Zero to Spring Boot Hero with GitHub CodespacesVMware Tanzu
 
JAVA Collections frame work ppt
 JAVA Collections frame work ppt JAVA Collections frame work ppt
JAVA Collections frame work pptRanjith Alappadan
 

More Related Content

What's hot

2.linear regression and logistic regression
2.linear regression and logistic regression2.linear regression and logistic regression
2.linear regression and logistic regressionHaesun Park
 
Evolution of the StyleGAN family
Evolution of the StyleGAN familyEvolution of the StyleGAN family
Evolution of the StyleGAN familyVitaly Bondar
 
Image captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptxImage captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptxMrUnknown820784
 
Generative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs)Generative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs)Amol Patil
 
PGL SUM Video Summarization
PGL SUM Video SummarizationPGL SUM Video Summarization
PGL SUM Video SummarizationVasileiosMezaris
 
文献紹介:Temporal Convolutional Networks for Action Segmentation and Detection
文献紹介:Temporal Convolutional Networks for Action Segmentation and Detection文献紹介:Temporal Convolutional Networks for Action Segmentation and Detection
文献紹介:Temporal Convolutional Networks for Action Segmentation and DetectionToru Tamaki
 
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
 A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs) A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)Thomas da Silva Paula
 
Session-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networksSession-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networksZimin Park
 
広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9
広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9
広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9Kazuhiro Ota
 
Neural Mask Generator : Learning to Generate Adaptive Word Maskings for Langu...
Neural Mask Generator : Learning to Generate Adaptive WordMaskings for Langu...Neural Mask Generator : Learning to Generate Adaptive WordMaskings for Langu...
Neural Mask Generator : Learning to Generate Adaptive Word Maskings for Langu...MLAI2
 
[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...
[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...
[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...Deep Learning JP
 
[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호
[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호
[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호NAVER D2
 
【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)
【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)
【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)ARISE analytics
 
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptxARISE analytics
 
GANの簡単な理解から正しい理解まで
GANの簡単な理解から正しい理解までGANの簡単な理解から正しい理解まで
GANの簡単な理解から正しい理解までKazuma Komiya
 
【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】
【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】
【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】YutaSuzuki27
 
[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksDeep Learning JP
 

What's hot (20)

Struts introduction
Struts introductionStruts introduction
Struts introduction
 
2.linear regression and logistic regression
2.linear regression and logistic regression2.linear regression and logistic regression
2.linear regression and logistic regression
 
Evolution of the StyleGAN family
Evolution of the StyleGAN familyEvolution of the StyleGAN family
Evolution of the StyleGAN family
 
Angular
AngularAngular
Angular
 
Image captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptxImage captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptx
 
分散表現を用いたリアルタイム学習型セッションベース推薦システム
分散表現を用いたリアルタイム学習型セッションベース推薦システム分散表現を用いたリアルタイム学習型セッションベース推薦システム
分散表現を用いたリアルタイム学習型セッションベース推薦システム
 
Generative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs)Generative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs)
 
PGL SUM Video Summarization
PGL SUM Video SummarizationPGL SUM Video Summarization
PGL SUM Video Summarization
 
文献紹介:Temporal Convolutional Networks for Action Segmentation and Detection
文献紹介:Temporal Convolutional Networks for Action Segmentation and Detection文献紹介:Temporal Convolutional Networks for Action Segmentation and Detection
文献紹介:Temporal Convolutional Networks for Action Segmentation and Detection
 
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
 A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs) A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
 
Session-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networksSession-based recommendations with recurrent neural networks
Session-based recommendations with recurrent neural networks
 
広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9
広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9
広告クリエイティブ制作におけるコンピュータビジョングラフィックデザイン CA Data Engineering & Data Analysis WS #9
 
Neural Mask Generator : Learning to Generate Adaptive Word Maskings for Langu...
Neural Mask Generator : Learning to Generate Adaptive WordMaskings for Langu...Neural Mask Generator : Learning to Generate Adaptive WordMaskings for Langu...
Neural Mask Generator : Learning to Generate Adaptive Word Maskings for Langu...
 
[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...
[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...
[DL輪読会]A Simple Unified Framework for Detecting Out-of-Distribution Samples a...
 
[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호
[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호
[221] 딥러닝을 이용한 지역 컨텍스트 검색 김진호
 
【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)
【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)
【論文読み会】Alias-Free Generative Adversarial Networks(StyleGAN3)
 
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
 
GANの簡単な理解から正しい理解まで
GANの簡単な理解から正しい理解までGANの簡単な理解から正しい理解まで
GANの簡単な理解から正しい理解まで
 
【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】
【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】
【学会発表】U-Net++とSE-Netを統合した画像セグメンテーションのための転移学習モデル【IBIS2020】
 
[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
[DL輪読会]EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
 

Similar to M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020)

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...ALINLAB
 
Thamme Gowda's PhD dissertation defense slides
Thamme Gowda's PhD dissertation defense slidesThamme Gowda's PhD dissertation defense slides
Thamme Gowda's PhD dissertation defense slidesThamme Gowda
 
Grammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world ApplicabilityGrammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world ApplicabilityMasato Mita
 
Neural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain ShiftNeural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain ShiftSebastian Ruder
 
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...MLAI2
 
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...広樹 本間
 
Présentation d'une communication acceptée dans Iceri2019
Présentation d'une communication acceptée dans Iceri2019Présentation d'une communication acceptée dans Iceri2019
Présentation d'une communication acceptée dans Iceri2019Thouraya Daouas
 
Wharton People Analytics Conference 2017
Wharton People Analytics Conference 2017Wharton People Analytics Conference 2017
Wharton People Analytics Conference 2017Janmejay Dave
 
HAR-MI method for multi-class imbalanced datasets
HAR-MI method for multi-class imbalanced datasetsHAR-MI method for multi-class imbalanced datasets
HAR-MI method for multi-class imbalanced datasetsTELKOMNIKA JOURNAL
 
NLG, Training, Inference & Evaluation
NLG, Training, Inference & Evaluation NLG, Training, Inference & Evaluation
NLG, Training, Inference & Evaluation Deep Learning Italia
 
[CVPR 22] Context-rich Minority Oversampling for Long-tailed Classification
[CVPR 22] Context-rich Minority Oversampling for Long-tailed Classification[CVPR 22] Context-rich Minority Oversampling for Long-tailed Classification
[CVPR 22] Context-rich Minority Oversampling for Long-tailed ClassificationSeulki Park
 
Rough ready and rapid guide to TESTA
Rough ready and rapid guide to TESTARough ready and rapid guide to TESTA
Rough ready and rapid guide to TESTATansy Jessop
 
(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised LearningYamato OKAMOTO
 
CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...
CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...
CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...Antonio Tejero de Pablos
 
ML Interpretability Inside Out
ML Interpretability Inside OutML Interpretability Inside Out
ML Interpretability Inside OutMara Graziani
 

Similar to M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) (15)

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised...
 
Thamme Gowda's PhD dissertation defense slides
Thamme Gowda's PhD dissertation defense slidesThamme Gowda's PhD dissertation defense slides
Thamme Gowda's PhD dissertation defense slides
 
Grammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world ApplicabilityGrammatical Error Correction with Improved Real-world Applicability
Grammatical Error Correction with Improved Real-world Applicability
 
Neural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain ShiftNeural Semi-supervised Learning under Domain Shift
Neural Semi-supervised Learning under Domain Shift
 
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
 
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
2019 dynamically composing_domain-data_selection_with_clean-data_selection_by...
 
Présentation d'une communication acceptée dans Iceri2019
Présentation d'une communication acceptée dans Iceri2019Présentation d'une communication acceptée dans Iceri2019
Présentation d'une communication acceptée dans Iceri2019
 
Wharton People Analytics Conference 2017
Wharton People Analytics Conference 2017Wharton People Analytics Conference 2017
Wharton People Analytics Conference 2017
 
HAR-MI method for multi-class imbalanced datasets
HAR-MI method for multi-class imbalanced datasetsHAR-MI method for multi-class imbalanced datasets
HAR-MI method for multi-class imbalanced datasets
 
NLG, Training, Inference & Evaluation
NLG, Training, Inference & Evaluation NLG, Training, Inference & Evaluation
NLG, Training, Inference & Evaluation
 
[CVPR 22] Context-rich Minority Oversampling for Long-tailed Classification
[CVPR 22] Context-rich Minority Oversampling for Long-tailed Classification[CVPR 22] Context-rich Minority Oversampling for Long-tailed Classification
[CVPR 22] Context-rich Minority Oversampling for Long-tailed Classification
 
Rough ready and rapid guide to TESTA
Rough ready and rapid guide to TESTARough ready and rapid guide to TESTA
Rough ready and rapid guide to TESTA
 
(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning
 
CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...
CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...
CVPR2022 paper reading - Balanced multimodal learning - All Japan Computer Vi...
 
ML Interpretability Inside Out
ML Interpretability Inside OutML Interpretability Inside Out
ML Interpretability Inside Out
 

More from ALINLAB

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...ALINLAB
 
Learning bounds for risk-sensitive learning
Learning bounds for risk-sensitive learningLearning bounds for risk-sensitive learning
Learning bounds for risk-sensitive learningALINLAB
 
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...ALINLAB
 
Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)
Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)
Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)ALINLAB
 
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...ALINLAB
 
Self-supervised Label Augmentation via Input Transformations (ICML 2020)
Self-supervised Label Augmentation via Input Transformations (ICML 2020)Self-supervised Label Augmentation via Input Transformations (ICML 2020)
Self-supervised Label Augmentation via Input Transformations (ICML 2020)ALINLAB
 

More from ALINLAB (6)

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...
Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinf...
 
Learning bounds for risk-sensitive learning
Learning bounds for risk-sensitive learningLearning bounds for risk-sensitive learning
Learning bounds for risk-sensitive learning
 
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted I...
 
Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)
Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)
Polynomial Tensor Sketch for Element-wise Matrix Function (ICML 2020)
 
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement ...
 
Self-supervised Label Augmentation via Input Transformations (ICML 2020)
Self-supervised Label Augmentation via Input Transformations (ICML 2020)Self-supervised Label Augmentation via Input Transformations (ICML 2020)
Self-supervised Label Augmentation via Input Transformations (ICML 2020)
 

Recently uploaded

Traffic Signboard Classification with Voice alert to the driver.pptx
Traffic Signboard Classification with Voice alert to the driver.pptxTraffic Signboard Classification with Voice alert to the driver.pptx
Traffic Signboard Classification with Voice alert to the driver.pptxharimaxwell0712
 
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...ISPMAIndia
 
Confoo 2024 Gettings started with OpenAI and data science
Confoo 2024 Gettings started with OpenAI and data scienceConfoo 2024 Gettings started with OpenAI and data science
Confoo 2024 Gettings started with OpenAI and data scienceSusan Ibach
 
My sample product research idea for you!
My sample product research idea for you!My sample product research idea for you!
My sample product research idea for you!KivenRaySarsaba
 
"Running Open-Source LLM models on Kubernetes", Volodymyr Tsap
"Running Open-Source LLM models on Kubernetes",  Volodymyr Tsap"Running Open-Source LLM models on Kubernetes",  Volodymyr Tsap
"Running Open-Source LLM models on Kubernetes", Volodymyr TsapFwdays
 
Leveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docx
Leveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docxLeveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docx
Leveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docxVotarikari Shravan
 
Bit N Build Poland
Bit N Build PolandBit N Build Poland
Bit N Build PolandGDSC PJATK
 
How we think about an advisor tech stack
How we think about an advisor tech stackHow we think about an advisor tech stack
How we think about an advisor tech stackSummit
 
"Testing of Helm Charts or There and Back Again", Yura Rochniak
"Testing of Helm Charts or There and Back Again", Yura Rochniak"Testing of Helm Charts or There and Back Again", Yura Rochniak
"Testing of Helm Charts or There and Back Again", Yura RochniakFwdays
 
Power of 2024 - WITforce Odyssey.pptx.pdf
Power of 2024 - WITforce Odyssey.pptx.pdfPower of 2024 - WITforce Odyssey.pptx.pdf
Power of 2024 - WITforce Odyssey.pptx.pdfkatalinjordans1
 
Campotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company ProfileCampotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company ProfileCampotelPhilippines
 
Battle of React State Managers in frontend applications
Battle of React State Managers in frontend applicationsBattle of React State Managers in frontend applications
Battle of React State Managers in frontend applicationsEvangelia Mitsopoulou
 
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...UiPathCommunity
 
Building Products That Think- Bhaskaran Srinivasan & Ashish Gupta
Building Products That Think- Bhaskaran Srinivasan & Ashish GuptaBuilding Products That Think- Bhaskaran Srinivasan & Ashish Gupta
Building Products That Think- Bhaskaran Srinivasan & Ashish GuptaISPMAIndia
 
Artificial-Intelligence-in-Marketing-Data.pdf
Artificial-Intelligence-in-Marketing-Data.pdfArtificial-Intelligence-in-Marketing-Data.pdf
Artificial-Intelligence-in-Marketing-Data.pdfIsidro Navarro
 
"Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre...
"Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre..."Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre...
"Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre...shaiyuvasv
 
Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...
Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...
Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...Product School
 
Automate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center ExcellenceAutomate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center ExcellencePrecisely
 
Importance of magazines in education ppt
Importance of magazines in education pptImportance of magazines in education ppt
Importance of magazines in education pptsafnarafeek2002
 

Recently uploaded (20)

Traffic Signboard Classification with Voice alert to the driver.pptx
Traffic Signboard Classification with Voice alert to the driver.pptxTraffic Signboard Classification with Voice alert to the driver.pptx
Traffic Signboard Classification with Voice alert to the driver.pptx
 
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
AI MODELS USAGE IN FINTECH PRODUCTS: PM APPROACH & BEST PRACTICES by Kasthuri...
 
Confoo 2024 Gettings started with OpenAI and data science
Confoo 2024 Gettings started with OpenAI and data scienceConfoo 2024 Gettings started with OpenAI and data science
Confoo 2024 Gettings started with OpenAI and data science
 
My sample product research idea for you!
My sample product research idea for you!My sample product research idea for you!
My sample product research idea for you!
 
"Running Open-Source LLM models on Kubernetes", Volodymyr Tsap
"Running Open-Source LLM models on Kubernetes",  Volodymyr Tsap"Running Open-Source LLM models on Kubernetes",  Volodymyr Tsap
"Running Open-Source LLM models on Kubernetes", Volodymyr Tsap
 
Leveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docx
Leveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docxLeveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docx
Leveraging SLF4j for Effective Logging in IBM App Connect Enterprise.docx
 
In sharing we trust. Taking advantage of a diverse consortium to build a tran...
In sharing we trust. Taking advantage of a diverse consortium to build a tran...In sharing we trust. Taking advantage of a diverse consortium to build a tran...
In sharing we trust. Taking advantage of a diverse consortium to build a tran...
 
Bit N Build Poland
Bit N Build PolandBit N Build Poland
Bit N Build Poland
 
How we think about an advisor tech stack
How we think about an advisor tech stackHow we think about an advisor tech stack
How we think about an advisor tech stack
 
"Testing of Helm Charts or There and Back Again", Yura Rochniak
"Testing of Helm Charts or There and Back Again", Yura Rochniak"Testing of Helm Charts or There and Back Again", Yura Rochniak
"Testing of Helm Charts or There and Back Again", Yura Rochniak
 
Power of 2024 - WITforce Odyssey.pptx.pdf
Power of 2024 - WITforce Odyssey.pptx.pdfPower of 2024 - WITforce Odyssey.pptx.pdf
Power of 2024 - WITforce Odyssey.pptx.pdf
 
Campotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company ProfileCampotel: Telecommunications Infra and Network Builder - Company Profile
Campotel: Telecommunications Infra and Network Builder - Company Profile
 
Battle of React State Managers in frontend applications
Battle of React State Managers in frontend applicationsBattle of React State Managers in frontend applications
Battle of React State Managers in frontend applications
 
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
Dev Dives: Leverage APIs and Gen AI to power automations for RPA and software...
 
Building Products That Think- Bhaskaran Srinivasan & Ashish Gupta
Building Products That Think- Bhaskaran Srinivasan & Ashish GuptaBuilding Products That Think- Bhaskaran Srinivasan & Ashish Gupta
Building Products That Think- Bhaskaran Srinivasan & Ashish Gupta
 
Artificial-Intelligence-in-Marketing-Data.pdf
Artificial-Intelligence-in-Marketing-Data.pdfArtificial-Intelligence-in-Marketing-Data.pdf
Artificial-Intelligence-in-Marketing-Data.pdf
 
"Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre...
"Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre..."Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre...
"Journey of Aspiration: Unveiling the Path to Becoming a Technocrat and Entre...
 
Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...
Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...
Harnessing the Power of GenAI for Exceptional Product Outcomes by Booking.com...
 
Automate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center ExcellenceAutomate Your Master Data Processes for Shared Service Center Excellence
Automate Your Master Data Processes for Shared Service Center Excellence
 
Importance of magazines in education ppt
Importance of magazines in education pptImportance of magazines in education ppt
Importance of magazines in education ppt
 

M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020)

  • 1. M2m: Imbalanced Classification via Major-to-minor Translation Jaehyung Kim* Jongheon Jeong* Jinwoo Shin *Equal contribution Korea Advanced Institute of Science and Technology (KAIST)
  • 2. • Many real-world datasets have imbalanced class distributions • Standard training (e.g. ERM) often fails to generalize at the “tail” classes [Wang et al. 2017; Cui et al. 2019; Cao et al. 2019] Class Imbalance in Training Data Species [Van Horn et al. 2019] Places [Wang et al. 2017] [Wang et al. 2017] Learning to Model the Tail. NeurIPS, 2017 [Van Horn et al. 2019] The iNaturalist Species Classification and Detection Dataset. In CVPR, 2018 [Cao et al. 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. In NeurIPS 2019 [Cui et al. 2019] Class-balanced Loss Based on Effective Number of Samples. In CVPR, 2019
  • 3. • Many real-world datasets have imbalanced class distributions • Standard training (e.g. ERM) often fails to generalize at the “tail” classes [Wang et al. 2017; Cui et al. 2019; Cao et al. 2019] • Several training strategies have been investigated Class Imbalance in Training Data Re-balancing methods • Re-sampling [Japkowicz et al. 2000; Chawla et al. 2002] • Re-weighting [Khan et al. 2017; Cui et al. 2019] Regularization methods • Margin-based method [Dong et al. 2017; Cao et al. 2019] • Minority focused loss [Lin et al. 2017] Fundamental problem: Limited information of minority classes [Japkowicz et al. 2000] The Class Imbalance Problem: Significance and Strategies. In ICAI 2000 [Chawla et al. 2002] SMOTE: Synthetic Minority Oversampling Technique. In JAIR 2002 [Khan et al. 2017] Cost-sensitive Learning of Deep Feature Representations from Imbalanced Data. In TNNLS 2017 [Dong et al. 2018] Imbalanced Deep Learning by Minority Class Incremental Rectification., TPAMI 2018 [Lin et al. 2017] Focal Loss for Dense Object Detection., CVPR 2017
  • 4. • M2m augments minority classes using information of majority samples • Over-fitting on minority classes is prevented by utilizing the diversity of majority • A simple optimization using a pre-trained classifier surprisingly works well M2m: Major-to-minor Translation
  • 5. • M2m augments minority classes via translating from majority samples • Each translation is done by solving the following optimization: M2m: Major-to-minor Translation Optimization objective of M2m (a) Translation to minority class - Using a pre-trained classifier (b) Regularization for reducing a risk as majority class - On the logit of training classifier is used as a minority sample for training f<latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit><latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit><latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit><latexit sha1_base64="dC5uJX4s+XLUhctJUEqp/+YNQhw=">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</latexit> x⇤ <latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">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</latexit><latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">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</latexit><latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">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</latexit><latexit sha1_base64="xiLUe47ZeHY4KDuiiyZk9HZurI4=">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</latexit> k<latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit><latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit><latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit><latexit sha1_base64="OSVpthl7bZLrnH3UTqOtdanyPNQ=">AAAB6HicdVDLSsNAFL3xWeur6tLNYBFchaSmD3cFNy5bsA9oQ5lMp+3YySTMTIQS+gVuXCji1k9y5984aSuo6IELh3Pu5d57gpgzpR3nw1pb39jc2s7t5Hf39g8OC0fHbRUlktAWiXgkuwFWlDNBW5ppTruxpDgMOO0E0+vM79xTqVgkbvUspn6Ix4KNGMHaSM3poFB07ErF86pXyLHdS8+tlTPilMulGnJtZ4EirNAYFN77w4gkIRWacKxUz3Vi7adYakY4nef7iaIxJlM8pj1DBQ6p8tPFoXN0bpQhGkXSlNBooX6fSHGo1CwMTGeI9UT99jLxL6+X6FHNT5mIE00FWS4aJRzpCGVfoyGTlGg+MwQTycytiEywxESbbPImhK9P0f+kXTKx2G7TK9a9VRw5OIUzuAAXqlCHG2hACwhQeIAneLburEfrxXpdtq5Zq5kT+AHr7RNBDY0w</latexit> k0<latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit><latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit><latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit><latexit sha1_base64="yC+mOBKc1K9Cosnmd5PnqsiH0PU=">AAAB6nicdVDLSgMxFL3js9ZX1aWbYBFcDUlpte4KblxWtA9oh5JJ0zY0kxmSjFCGfoIbF4q49Yvc+TemD0FFD1w4nHMv994TJlIYi/GHt7K6tr6xmdvKb+/s7u0XDg6bJk414w0Wy1i3Q2q4FIo3rLCStxPNaRRK3grHVzO/dc+1EbG6s5OEBxEdKjEQjFon3Y57uFcoYh9XcIkQ5Ej1nFxiRyqkXClVEfHxHEVYot4rvHf7MUsjriyT1JgOwYkNMqqtYJJP893U8ISyMR3yjqOKRtwE2fzUKTp1Sh8NYu1KWTRXv09kNDJmEoWuM6J2ZH57M/Evr5PaQTXIhEpSyxVbLBqkEtkYzf5GfaE5s3LiCGVauFsRG1FNmXXp5F0IX5+i/0mz5BPsk5tysVZexpGDYziBMyBwATW4hjo0gMEQHuAJnj3pPXov3uuidcVbzhzBD3hvn0WDjb4=</latexit>
  • 6. • Rejection criterion: selective use of translated sample • This reduces a risk of unreliable generation when is small • Optimal sampling : better choice of majority seed • Majority classes to sample are selected by considering two aspects: (a) Maximizes the acceptance probability (b) Chooses diverse classes M2m: Techniques for Better Efficiency x⇤ <latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit><latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit><latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit><latexit sha1_base64="F1KMxJXvEGNv3MpOrIRy7Tp7EXs=">AAAB7HicbVA9SwNBEJ2LXzF+RS1tFoMgFuFOBC0sAjaWEbwkkJxhbzNJluztHbt7YjjyG2wsFLH1B9n5b9wkV2jig4HHezPMzAsTwbVx3W+nsLK6tr5R3Cxtbe/s7pX3Dxo6ThVDn8UiVq2QahRcom+4EdhKFNIoFNgMRzdTv/mISvNY3ptxgkFEB5L3OaPGSv7TQ3Y26ZYrbtWdgSwTLycVyFHvlr86vZilEUrDBNW67bmJCTKqDGcCJ6VOqjGhbEQH2LZU0gh1kM2OnZATq/RIP1a2pCEz9fdERiOtx1FoOyNqhnrRm4r/ee3U9K+CjMskNSjZfFE/FcTEZPo56XGFzIixJZQpbm8lbEgVZcbmU7IheIsvL5PGedVzq97dRaV2ncdRhCM4hlPw4BJqcAt18IEBh2d4hTdHOi/Ou/Mxby04+cwh/IHz+QPCTo6e</latexit> x0<latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit><latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit><latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit><latexit sha1_base64="5huwj3zFVPbko7iCRKaz92eG43g=">AAAB7HicbVBNS8NAEJ3Ur1q/qh69LBbBU0lE0IOHghePFUxbaEPZbCft0s0m7G7EEvobvHhQxKs/yJv/xm2bg7Y+GHi8N8PMvDAVXBvX/XZKa+sbm1vl7crO7t7+QfXwqKWTTDH0WSIS1QmpRsEl+oYbgZ1UIY1Dge1wfDvz24+oNE/kg5mkGMR0KHnEGTVW8p/6uTvtV2tu3Z2DrBKvIDUo0OxXv3qDhGUxSsME1brruakJcqoMZwKnlV6mMaVsTIfYtVTSGHWQz4+dkjOrDEiUKFvSkLn6eyKnsdaTOLSdMTUjvezNxP+8bmai6yDnMs0MSrZYFGWCmITMPicDrpAZMbGEMsXtrYSNqKLM2HwqNgRv+eVV0rqoe27du7+sNW6KOMpwAqdwDh5cQQPuoAk+MODwDK/w5kjnxXl3PhatJaeYOYY/cD5/AMzzjqU=</latexit> # samples of class Nk0<latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">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</latexit><latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">AAACynicjVHLSsNAFD2Nr1pfVZdugkVwVRIR7LLgxoVIBfuAWkoyndaheTGZCKV05w+41Q8T/0D/wjtjCmoRnZDkzLnn3Jl7r58EIlWO81qwlpZXVteK66WNza3tnfLuXiuNM8l4k8VBLDu+l/JARLyphAp4J5HcC/2At/3xuY6377lMRRzdqEnCe6E3isRQME8R1b7qT8d9Z9YvV5yqY5a9CNwcVJCvRlx+wS0GiMGQIQRHBEU4gIeUni5cOEiI62FKnCQkTJxjhhJ5M1JxUnjEjuk7ol03ZyPa65ypcTM6JaBXktPGEXli0knC+jTbxDOTWbO/5Z6anPpuE/r7ea6QWIU7Yv/yzZX/9elaFIaomRoE1ZQYRlfH8iyZ6Yq+uf2lKkUZEuI0HlBcEmbGOe+zbTypqV331jPxN6PUrN6zXJvhXd+SBuz+HOciaJ1UXafqXp9W6rV81EUc4BDHNM8z1HGBBpqmykc84dm6tKQ1saafUquQe/bxbVkPH298kdY=</latexit><latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">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</latexit><latexit sha1_base64="8Ml4gG7BbFmCtUqx3C4PlF933m0=">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</latexit> major minor Q(k0|k) / 1 (Nk0 Nk)+ <latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">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</latexit><latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">AAAC8nicjVHLSsNAFD3G97vq0s1gESrSkoioS8GNq1LBqmA1JHHUkDQTJhOh1H6FO3fi1h9wqx8h/oH+hXfGCD4QnZDkzLn3nJl7r5/GYaZs+7nP6h8YHBoeGR0bn5icmi7NzO5lIpcBbwYiFvLA9zIehwlvqlDF/CCV3Gv7Md/3oy0d37/gMgtFsqs6KT9qe2dJeBoGniLKLVV3KpFrX7JoibVSKVIlmMOqrOVz5R13K3W3S+Fete5GS8fLPbdUtmu2WewncApQRrEaovSEFk4gECBHGxwJFOEYHjJ6DuHARkrcEbrESUKhiXP0MEbanLI4ZXjERvQ9o91hwSa0156ZUQd0SkyvJCXDImkE5UnC+jRm4rlx1uxv3l3jqe/Wob9feLWJVTgn9i/dR+Z/dboWhVNsmBpCqik1jK4uKFxy0xV9c/apKkUOKXEan1BcEg6M8qPPzGgyU7vurWfiLyZTs3ofFLk5XvUtacDO93H+BHsrNceuOTur5c21YtQjmMcCKjTPdWxiGw00yfsK93jAo6Wsa+vGun1PtfoKzRy+LOvuDS/0n28=</latexit><latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">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</latexit><latexit sha1_base64="4P/5yGI7mPJRAOS+dUzL1rT5mFA=">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</latexit> Q(k0|k)<latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit><latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit><latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit><latexit sha1_base64="JOFzpi7JU8iyOJ7GwGax5fw+8L8=">AAAB73icbVA9SwNBEJ2LXzF+RS1tFoMQm7AnghYWARvLBMwHJEfY2+wly+3tnbt7QjjzJ2wsFLH179j5b9wkV2jig4HHezPMzPMTwbXB+NsprK1vbG4Vt0s7u3v7B+XDo7aOU0VZi8YiVl2faCa4ZC3DjWDdRDES+YJ1/PB25ncemdI8lvdmkjAvIiPJA06JsVK3WQ0H+Ck8H5QruIbnQKvEzUkFcjQG5a/+MKZpxKShgmjdc3FivIwow6lg01I/1SwhNCQj1rNUkohpL5vfO0VnVhmiIFa2pEFz9fdERiKtJ5FvOyNixnrZm4n/eb3UBNdexmWSGibpYlGQCmRiNHseDbli1IiJJYQqbm9FdEwUocZGVLIhuMsvr5L2Rc3FNbd5Wanf5HEU4QROoQouXEEd7qABLaAg4Ble4c15cF6cd+dj0Vpw8plj+APn8wcIdY9H</latexit>
  • 7. • Two evaluation metrics for imbalanced classification models: • Balanced accuracy (bACC): arithmetic mean over class-wise sensitivity • Geometric mean scores (GM): geometric mean over class-wise sensitivity • Various types of baseline methods • Re-sampling (RS) and re-weighting (RW) • Re-sampling variants: SMOTE, deferred re-sampling (DRS) [Chawla et al. 2002; Cao et al. 2019] • Re-weighting variants: class-balanced RW (CB-RW) [Cui et al. 2019] • Minority regularization: focal loss (Focal), label-dist. aware margin (LDAM) [Lin et al. 2017; Cao et al. 2019] Experiments [Chawla et al. 2002] SMOTE: Synthetic Minority Oversampling Technique. In JAIR 2002 [Lin et al. 2017] Focal Loss for Dense Object Detection., CVPR 2017 [Cao et al. 2019] Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. In NeurIPS 2019 [Cui et al. 2019] Class-balanced Loss Based on Effective Number of Samples. In CVPR, 2019
  • 8. • Synthetically imbalanced version of CIFAR-10/100 • We control the imbalance ratio • are set to follow an exponential decay across Experiments: Long-tailed CIFAR-10/100 ⇢ = N1/Nk<latexit sha1_base64="NwvRw269Yl0ESgPSsPYYzPTnY3I=">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</latexit><latexit sha1_base64="NwvRw269Yl0ESgPSsPYYzPTnY3I=">AAAC13icjVHLSsNAFD3GV62vWJdugkVwVRMR7EYouHElFexD2lKSdNqGpkmYTMRSijtx6w+41T8S/0D/wjtjCmoRnZCZM+fec2buXCfyvViY5uucNr+wuLScWcmurq1vbOpbuWocJtxlFTf0Q1537Jj5XsAqwhM+q0ec2UPHZzVncCrjtWvGYy8MLsUoYq2h3Qu8rufagqi2nmvyfmicGOftsTU5oHkwaet5s2CqYcwCKwV5pKMc6i9oooMQLhIMwRBAEPZhI6avAQsmIuJaGBPHCXkqzjBBlrQJZTHKsIkd0NyjXSNlA9pLz1ipXTrFp5+T0sAeaULK44TlaYaKJ8pZsr95j5WnvNuIVif1GhIr0Cf2L9008786WYtAF0VVg0c1RYqR1bmpS6JeRd7c+FKVIIeIOIk7FOeEXaWcvrOhNLGqXb6treJvKlOycu+muQne5S2pwdbPds6C6mHBMgvWxVG+VExbncEOdrFP/TxGCWcoo0LeN3jEE561K+1Wu9PuP1O1uVSzjW9De/gAVqKWDQ==</latexit><latexit sha1_base64="NwvRw269Yl0ESgPSsPYYzPTnY3I=">AAAC13icjVHLSsNAFD3GV62vWJdugkVwVRMR7EYouHElFexD2lKSdNqGpkmYTMRSijtx6w+41T8S/0D/wjtjCmoRnZCZM+fec2buXCfyvViY5uucNr+wuLScWcmurq1vbOpbuWocJtxlFTf0Q1537Jj5XsAqwhM+q0ec2UPHZzVncCrjtWvGYy8MLsUoYq2h3Qu8rufagqi2nmvyfmicGOftsTU5oHkwaet5s2CqYcwCKwV5pKMc6i9oooMQLhIMwRBAEPZhI6avAQsmIuJaGBPHCXkqzjBBlrQJZTHKsIkd0NyjXSNlA9pLz1ipXTrFp5+T0sAeaULK44TlaYaKJ8pZsr95j5WnvNuIVif1GhIr0Cf2L9008786WYtAF0VVg0c1RYqR1bmpS6JeRd7c+FKVIIeIOIk7FOeEXaWcvrOhNLGqXb6treJvKlOycu+muQne5S2pwdbPds6C6mHBMgvWxVG+VExbncEOdrFP/TxGCWcoo0LeN3jEE561K+1Wu9PuP1O1uVSzjW9De/gAVqKWDQ==</latexit><latexit sha1_base64="NwvRw269Yl0ESgPSsPYYzPTnY3I=">AAAC13icjVHLSsNAFD3GV62vWJdugkVwVRMR7EYouHElFexD2lKSdNqGpkmYTMRSijtx6w+41T8S/0D/wjtjCmoRnZCZM+fec2buXCfyvViY5uucNr+wuLScWcmurq1vbOpbuWocJtxlFTf0Q1537Jj5XsAqwhM+q0ec2UPHZzVncCrjtWvGYy8MLsUoYq2h3Qu8rufagqi2nmvyfmicGOftsTU5oHkwaet5s2CqYcwCKwV5pKMc6i9oooMQLhIMwRBAEPZhI6avAQsmIuJaGBPHCXkqzjBBlrQJZTHKsIkd0NyjXSNlA9pLz1ipXTrFp5+T0sAeaULK44TlaYaKJ8pZsr95j5WnvNuIVif1GhIr0Cf2L9008786WYtAF0VVg0c1RYqR1bmpS6JeRd7c+FKVIIeIOIk7FOeEXaWcvrOhNLGqXb6treJvKlOycu+muQne5S2pwdbPds6C6mHBMgvWxVG+VExbncEOdrFP/TxGCWcoo0LeN3jEE561K+1Wu9PuP1O1uVSzjW9De/gAVqKWDQ==</latexit> M2m surpasses all the baselines tested M2m further improves existing regularization Nk<latexit sha1_base64="wk8D3NDoQs7Lt/vJBl8Aiej2MHo=">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</latexit><latexit sha1_base64="wk8D3NDoQs7Lt/vJBl8Aiej2MHo=">AAACyHicjVHLSsNAFD2Nr/quunQTLIKrkohglwU34kIqmLZQS0mm0zo0TcJkopTSjT/gVr9M/AP9C++MKahFdEKSM+fec2buvUESilQ5zmvBWlhcWl4prq6tb2xubZd2dhtpnEnGPRaHsWwFfspDEXFPCRXyViK5PwpC3gyGZzrevOMyFXF0rcYJ74z8QST6gvmKKO+yOxlOu6WyU3HMsueBm4My8lWPSy+4QQ8xGDKMwBFBEQ7hI6WnDRcOEuI6mBAnCQkT55hijbQZZXHK8Ikd0ndAu3bORrTXnqlRMzolpFeS0sYhaWLKk4T1abaJZ8ZZs795T4ynvtuY/kHuNSJW4ZbYv3SzzP/qdC0KfVRNDYJqSgyjq2O5S2a6om9uf6lKkUNCnMY9ikvCzChnfbaNJjW16976Jv5mMjWr9yzPzfCub0kDdn+Ocx40jiuuU3GvTsq1aj7qIvZxgCOa5ylqOEcdHnkLPOIJz9aFlVj31vgz1Srkmj18W9bDB8wYkTM=</latexit><latexit sha1_base64="wk8D3NDoQs7Lt/vJBl8Aiej2MHo=">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</latexit><latexit sha1_base64="wk8D3NDoQs7Lt/vJBl8Aiej2MHo=">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</latexit> k<latexit sha1_base64="VJ9SyfzSOjNOMVbxQ3SrUcGK1J0=">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</latexit><latexit sha1_base64="VJ9SyfzSOjNOMVbxQ3SrUcGK1J0=">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</latexit><latexit sha1_base64="VJ9SyfzSOjNOMVbxQ3SrUcGK1J0=">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</latexit><latexit sha1_base64="VJ9SyfzSOjNOMVbxQ3SrUcGK1J0=">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</latexit>
  • 9. • Datasets with natural imbalances • Vision tasks: CelebA-5 and SUN397 • NLP tasks: Twitter and Reuters • Tend to have a much significant imbalance Experiments: Real-world Imbalanced Datasets M2m works even better under a harsh imbalance
  • 10. • A simple yet powerful over-sampling for imbalanced classification • Diversity of majority is effective to overcome the scarcity of minority • Adversarial examples could be a good feature at least for the minority Conclusion Thank you for your attention 😄