Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
M2m: Imbalanced Classification via
Major-to-minor Translation
Jaehyung Kim* Jongheon Jeong* Jinwoo Shin
*Equal contributio...
• Many real-world datasets have imbalanced class distributions
• Standard training (e.g. ERM) often fails to generalize at...
• Many real-world datasets have imbalanced class distributions
• Standard training (e.g. ERM) often fails to generalize at...
• M2m augments minority classes using information of majority samples
• Over-fitting on minority classes is prevented by u...
• M2m augments minority classes via translating from majority samples
• Each translation is done by solving the following ...
• Rejection criterion: selective use of translated sample
• This reduces a risk of unreliable generation when is small
• O...
• Two evaluation metrics for imbalanced classification models:
• Balanced accuracy (bACC): arithmetic mean over class-wise...
• Synthetically imbalanced version of CIFAR-10/100
• We control the imbalance ratio
• are set to follow an exponential dec...
• Datasets with natural imbalances
• Vision tasks: CelebA-5 and SUN397
• NLP tasks: Twitter and Reuters
• Tend to have a m...
• A simple yet powerful over-sampling for imbalanced classification
• Diversity of majority is effective to overcome the s...
Upcoming SlideShare
Loading in …5
×

of

M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 1 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 2 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 3 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 4 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 5 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 6 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 7 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 8 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 9 M2m: Imbalanced Classification via Major-to-minor Translation (CVPR 2020) Slide 10
Upcoming SlideShare
What to Upload to SlideShare
Next
Download to read offline and view in fullscreen.

2 Likes

Share

Download to read offline

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

Download to read offline

Jaehyung Kim*, Jongheon Jeong*, Jinwoo Shin

arXiv: https://arxiv.org/abs/2004.00431
code: https://github.com/alinlab/M2m

Related Books

Free with a 30 day trial from Scribd

See all

Related Audiobooks

Free with a 30 day trial from Scribd

See all

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

  1. 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. 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. 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. 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. 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=">AAACxHicjVHLSsNAFD2Nr1pfVZdugkVwVRIp6LIgiMsW7ANqkSSd1tBpEmYmQin6A27128Q/0L/wzjgFtYhOSHLm3HvOzL03zHgslee9Fpyl5ZXVteJ6aWNza3unvLvXlmkuItaKUp6KbhhIxuOEtVSsOOtmggWTkLNOOD7X8c4dEzJOkys1zVh/EoySeBhHgSKqObwpV7yqZ5a7CHwLKrCrkZZfcI0BUkTIMQFDAkWYI4CkpwcfHjLi+pgRJwjFJs5wjxJpc8pilBEQO6bviHY9yya0157SqCM6hdMrSOniiDQp5QnC+jTXxHPjrNnfvGfGU99tSv/Qek2IVbgl9i/dPPO/Ol2LwhBnpoaYasoMo6uLrEtuuqJv7n6pSpFDRpzGA4oLwpFRzvvsGo00teveBib+ZjI1q/eRzc3xrm9JA/Z/jnMRtE+qvlf1m7VKvWZHXcQBDnFM8zxFHZdooGW8H/GEZ+fC4Y508s9Up2A1+/i2nIcPPCaPXQ==</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. 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=">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</latexit><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> 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=">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</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. 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. 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=">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</latexit><latexit sha1_base64="NwvRw269Yl0ESgPSsPYYzPTnY3I=">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</latexit><latexit sha1_base64="NwvRw269Yl0ESgPSsPYYzPTnY3I=">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</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=">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</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. 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. 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 😄
  • HadiZand

    Apr. 1, 2021
  • myunghunchae

    May. 19, 2020

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

Views

Total views

923

On Slideshare

0

From embeds

0

Number of embeds

0

Actions

Downloads

8

Shares

0

Comments

0

Likes

2

×