SlideShare a Scribd company logo
1 of 13
Download to read offline
Fighting Fire with Fire: Contrastive Debiasing
without Bias-free Data
via Generative Bias-transformation
Yeonsung Jung, Hajin Shim, June Yong Yang, Eunho Yang
Korea Advanced Institute of Science and Technology (KAIST)
ICML 2023
• Deep neural networks easily rely on the malignant biases as shortcuts.
• Malignant bias
• Colored MNIST: Digits (task) and Color (malignant bias)
• Addressing bias problem is crucial in real-world applications.
• Significant consequences for domains such as healthcare or autonomous driving.
What is Debiasing?
2
[1] Lee et al., Learning Debiased Representation via Disentangled Feature Augmentation, NeurIPS’2021
Colored MNIST [1]
Biased samples
(Bias-aligned samples)
Bias-free samples
(Bias-conflicting samples)
• Existing works focus on identifying and emphasizing handful bias-free samples.
• Even though bias-aligned samples are the majority and also contain valuable task-
related information, they are often underutilized or even discarded.
• Also, previous methods easily break down in regimes where bias-free samples are
scarce or absent.
Motivation
3
Bias-aligned samples Bias-free samples
≪
(Minority)
(Majority)
< Previous >
• Existing works focus on identifying and emphasizing handful bias-free samples.
• Even though bias-aligned samples are the majority and also contain valuable task-
related information, they are often underutilized or even discarded.
• Also, previous methods easily break down in regimes where bias-free samples are
scarce or absent.
• Let’s focus on utilizing abundant bias-aligned samples.
Motivation
4
Bias-aligned samples Bias-free samples
< Ours >
≪
(Minority)
(Majority)
• Image translation models (e.g. CycleGAN[1], StarGAN[2]) render an image 𝑥 from a
source domain 𝑦 to a target domain 𝑦!.
• We hypothesize that in the case of biased dataset, the attributes representing the
the target domain 𝒚!
likely to be biased.
Synthesizing Bias-frees Samples via Image Translation Models
5
[1] Zhu at al., Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, ICCV’2017
[2] Choi et al., StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation, CVPR’2018
Image 𝑥
Translation
model
Output
Bias-aligned samples
Generated
Bias-free samples
Target domain 𝑦!
• We examine the behavior of the GAN-based images translation model, StarGAN, on
biased datasets.
• We observed that the domain discriminator of image translation models perceives
the malignant bias as the representative trait of the class 𝑦.
Image Translation Models Favor Malignant Bias.
6
Domain classification
Real/Fake
1) Lead the discriminator to be biased
Bias-transformed
Biased sample
Target class
<Training StarGAN with biased dataset>
Discriminator !
Generator "
#!
~%
• We examine the behavior of the GAN-based images translation model, StarGAN, on
biased datasets.
• We observed that the domain discriminator of image translation models perceives
the malignant bias as the representative trait of the class 𝑦.
• The accuracy of bias-aligned samples increases to nearly 100%.
Image Translation Models Favor Malignant Bias.
7
• We also observed that the biased domain classifier 𝐷"#$ induces a biased generator 𝐺
by optimizing the domain classification loss:
Image Translation Models Favor Malignant Bias.
8
ℒ"#$
%
= 𝔼(',))~𝒟,)!~𝒴[− log 𝐷"#$(𝑦!
|𝐺 𝑥, 𝑦!
)]
Domain classification
Real/Fake
1) Lead the discriminator to be biased
Bias-transformed
Biased sample
Target class
2) Lead the generator to translate bias features
<Training StarGAN with biased dataset>
Discriminator !
Generator "
#!~%
• We also observed that the biased domain classifier 𝐷"#$ induces a biased generator 𝐺
by optimizing the domain classification loss:
• Bias-translated images on various biased datasets.
Image Translation Models Favor Malignant Bias.
9
ℒ"#$
%
= 𝔼(',))~𝒟,)!~𝒴[− log 𝐷"#$(𝑦!
|𝐺 𝑥, 𝑦!
)]
• Fighting Fire with Fire: Pitting one bias type against another via contrastive
learning[1].
• Employing the bias-translation model as an augmentation method of contrastive learning.
• By contrasting the bias-aligned sample and the bias-transformed view against each
other, we can attenuate the bias while learning the task-related attributes.
Contrastive Debiasing via Generative Bias-transformation (CDvG)
10
<Whole framework>
!
"!
#"~% &′
&
(′
(
Maximize agreement by
Contrastive loss
Bias-transformed
View Generation
##~%
ℒ!"
ℒ!# +
Bias-transformed
!′
Biased sample
!
)!
~*
Encoder +
Pretrained ,
[1] Chen at al., A Simple Framework for Contrastive Learning of Visual Representations, ICML’2020
• Quantitative results
• Integration with the previous works which focus on bias-free samples (e.g. LfF).
Experiments
11
• Qualitative results
• Visualization of learned representations using T-SNE on Colored MNIST
• Visualization of Grad-CAM heatmaps on BFFHQ
Experiments
12
Thank you !
Any Questions ?

More Related Content

What's hot

Deep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageDeep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single image
Wei Yang
 

What's hot (20)

GAN in medical imaging
GAN in medical imagingGAN in medical imaging
GAN in medical imaging
 
General Tips for participating Kaggle Competitions
General Tips for participating Kaggle CompetitionsGeneral Tips for participating Kaggle Competitions
General Tips for participating Kaggle Competitions
 
Normalization 방법
Normalization 방법 Normalization 방법
Normalization 방법
 
Feature Engineering
Feature EngineeringFeature Engineering
Feature Engineering
 
Deep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageDeep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single image
 
Graph Convolutional Network 概説
Graph Convolutional Network 概説Graph Convolutional Network 概説
Graph Convolutional Network 概説
 
Generative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs)Generative Adversarial Networks (GANs)
Generative Adversarial Networks (GANs)
 
Emily Denton - Unsupervised Learning of Disentangled Representations from Vid...
Emily Denton - Unsupervised Learning of Disentangled Representations from Vid...Emily Denton - Unsupervised Learning of Disentangled Representations from Vid...
Emily Denton - Unsupervised Learning of Disentangled Representations from Vid...
 
Feature Engineering
Feature EngineeringFeature Engineering
Feature Engineering
 
Meta learning with memory augmented neural network
Meta learning with memory augmented neural networkMeta learning with memory augmented neural network
Meta learning with memory augmented neural network
 
(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning(SURVEY) Semi Supervised Learning
(SURVEY) Semi Supervised Learning
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
 
Cs231n 2017 lecture9 CNN Architecture
Cs231n 2017 lecture9 CNN ArchitectureCs231n 2017 lecture9 CNN Architecture
Cs231n 2017 lecture9 CNN Architecture
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human label
 
Gan intro
Gan introGan intro
Gan intro
 
Deep Learning for Computer Vision: Generative models and adversarial training...
Deep Learning for Computer Vision: Generative models and adversarial training...Deep Learning for Computer Vision: Generative models and adversarial training...
Deep Learning for Computer Vision: Generative models and adversarial training...
 
Attention Is All You Need
Attention Is All You NeedAttention Is All You Need
Attention Is All You Need
 
[DL輪読会]Encoder-Decoder with Atrous Separable Convolution for Semantic Image S...
[DL輪読会]Encoder-Decoder with Atrous Separable Convolution for Semantic Image S...[DL輪読会]Encoder-Decoder with Atrous Separable Convolution for Semantic Image S...
[DL輪読会]Encoder-Decoder with Atrous Separable Convolution for Semantic Image S...
 
Machine learning with graph
Machine learning with graphMachine learning with graph
Machine learning with graph
 

Similar to Y. Jung, ICML 2023, MLILAB, KAISTAI

لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
Egyptian Engineers Association
 
ageandgenderdetection-220802061020-9ee5a2cd.pptx
ageandgenderdetection-220802061020-9ee5a2cd.pptxageandgenderdetection-220802061020-9ee5a2cd.pptx
ageandgenderdetection-220802061020-9ee5a2cd.pptx
dhaliwalharsh055
 

Similar to Y. Jung, ICML 2023, MLILAB, KAISTAI (20)

brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANs
 
Generative Adversarial Networks and Their Applications in Medical Imaging
Generative Adversarial Networks  and Their Applications in Medical ImagingGenerative Adversarial Networks  and Their Applications in Medical Imaging
Generative Adversarial Networks and Their Applications in Medical Imaging
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
 
[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions
 
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESIMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
 
Graph Based Machine Learning with Applications to Media Analytics
Graph Based Machine Learning with Applications to Media AnalyticsGraph Based Machine Learning with Applications to Media Analytics
Graph Based Machine Learning with Applications to Media Analytics
 
Generational Adversarial Neural Networks - Essential Reference
Generational Adversarial Neural Networks - Essential ReferenceGenerational Adversarial Neural Networks - Essential Reference
Generational Adversarial Neural Networks - Essential Reference
 
Kaggle Gold Medal Case Study
Kaggle Gold Medal Case StudyKaggle Gold Medal Case Study
Kaggle Gold Medal Case Study
 
Generative Models for General Audiences
Generative Models for General AudiencesGenerative Models for General Audiences
Generative Models for General Audiences
 
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET TransformRotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
Rotation Invariant Face Recognition using RLBP, LPQ and CONTOURLET Transform
 
Artem Baklanov - Votes Aggregation Techniques in Geo-Wiki Crowdsourcing Game:...
Artem Baklanov - Votes Aggregation Techniques in Geo-Wiki Crowdsourcing Game:...Artem Baklanov - Votes Aggregation Techniques in Geo-Wiki Crowdsourcing Game:...
Artem Baklanov - Votes Aggregation Techniques in Geo-Wiki Crowdsourcing Game:...
 
Rsqrd AI - ML Interpretability: Beyond Feature Importance
Rsqrd AI - ML Interpretability: Beyond Feature ImportanceRsqrd AI - ML Interpretability: Beyond Feature Importance
Rsqrd AI - ML Interpretability: Beyond Feature Importance
 
Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...
 
Domain Transfer and Adaptation Survey
Domain Transfer and Adaptation SurveyDomain Transfer and Adaptation Survey
Domain Transfer and Adaptation Survey
 
Sub1586
Sub1586Sub1586
Sub1586
 
AGE AND GENDER DETECTION.pptx
AGE AND GENDER DETECTION.pptxAGE AND GENDER DETECTION.pptx
AGE AND GENDER DETECTION.pptx
 
ageandgenderdetection-220802061020-9ee5a2cd.pptx
ageandgenderdetection-220802061020-9ee5a2cd.pptxageandgenderdetection-220802061020-9ee5a2cd.pptx
ageandgenderdetection-220802061020-9ee5a2cd.pptx
 
Machine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdfMachine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdf
 

More from MLILAB

H. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AIH. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AI
MLILAB
 

More from MLILAB (20)

J. Jeong, AAAI 2024, MLILAB, KAIST AI..
J. Jeong,  AAAI 2024, MLILAB, KAIST AI..J. Jeong,  AAAI 2024, MLILAB, KAIST AI..
J. Jeong, AAAI 2024, MLILAB, KAIST AI..
 
J. Yun, NeurIPS 2023, MLILAB, KAISTAI
J. Yun,  NeurIPS 2023,  MLILAB,  KAISTAIJ. Yun,  NeurIPS 2023,  MLILAB,  KAISTAI
J. Yun, NeurIPS 2023, MLILAB, KAISTAI
 
S. Kim, NeurIPS 2023, MLILAB, KAISTAI
S. Kim,  NeurIPS 2023,  MLILAB,  KAISTAIS. Kim,  NeurIPS 2023,  MLILAB,  KAISTAI
S. Kim, NeurIPS 2023, MLILAB, KAISTAI
 
C. Kim, INTERSPEECH 2023, MLILAB, KAISTAI
C. Kim, INTERSPEECH 2023, MLILAB, KAISTAIC. Kim, INTERSPEECH 2023, MLILAB, KAISTAI
C. Kim, INTERSPEECH 2023, MLILAB, KAISTAI
 
J. Song, S. Kim, ICML 2023, MLILAB, KAISTAI
J. Song, S. Kim, ICML 2023, MLILAB, KAISTAIJ. Song, S. Kim, ICML 2023, MLILAB, KAISTAI
J. Song, S. Kim, ICML 2023, MLILAB, KAISTAI
 
K. Seo, ICASSP 2023, MLILAB, KAISTAI
K. Seo, ICASSP 2023, MLILAB, KAISTAIK. Seo, ICASSP 2023, MLILAB, KAISTAI
K. Seo, ICASSP 2023, MLILAB, KAISTAI
 
G. Kim, CVPR 2023, MLILAB, KAISTAI
G. Kim, CVPR 2023, MLILAB, KAISTAIG. Kim, CVPR 2023, MLILAB, KAISTAI
G. Kim, CVPR 2023, MLILAB, KAISTAI
 
S. Kim, ICLR 2023, MLILAB, KAISTAI
S. Kim, ICLR 2023, MLILAB, KAISTAIS. Kim, ICLR 2023, MLILAB, KAISTAI
S. Kim, ICLR 2023, MLILAB, KAISTAI
 
Y. Kim, ICLR 2023, MLILAB, KAISTAI
Y. Kim, ICLR 2023, MLILAB, KAISTAIY. Kim, ICLR 2023, MLILAB, KAISTAI
Y. Kim, ICLR 2023, MLILAB, KAISTAI
 
J. Yun, AISTATS 2022, MLILAB, KAISTAI
J. Yun, AISTATS 2022, MLILAB, KAISTAIJ. Yun, AISTATS 2022, MLILAB, KAISTAI
J. Yun, AISTATS 2022, MLILAB, KAISTAI
 
J. Song, J. Park, ICML 2022, MLILAB, KAISTAI
J. Song, J. Park, ICML 2022, MLILAB, KAISTAIJ. Song, J. Park, ICML 2022, MLILAB, KAISTAI
J. Song, J. Park, ICML 2022, MLILAB, KAISTAI
 
J. Park, J. Song, ICLR 2022, MLILAB, KAISTAI
J. Park, J. Song, ICLR 2022, MLILAB, KAISTAIJ. Park, J. Song, ICLR 2022, MLILAB, KAISTAI
J. Park, J. Song, ICLR 2022, MLILAB, KAISTAI
 
J. Park, H. Shim, AAAI 2022, MLILAB, KAISTAI
J. Park, H. Shim, AAAI 2022, MLILAB, KAISTAIJ. Park, H. Shim, AAAI 2022, MLILAB, KAISTAI
J. Park, H. Shim, AAAI 2022, MLILAB, KAISTAI
 
J. Park, AAAI 2022, MLILAB, KAIST AI
J. Park, AAAI 2022, MLILAB, KAIST AIJ. Park, AAAI 2022, MLILAB, KAIST AI
J. Park, AAAI 2022, MLILAB, KAIST AI
 
J. Song, et. al., ASRU 2021, MLILAB, KAIST AI
J. Song, et. al., ASRU 2021, MLILAB, KAIST AIJ. Song, et. al., ASRU 2021, MLILAB, KAIST AI
J. Song, et. al., ASRU 2021, MLILAB, KAIST AI
 
J. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AI
J. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AIJ. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AI
J. Song, H. Shim et al., ICASSP 2021, MLILAB, KAIST AI
 
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AIT. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
T. Yoon, et. al., ICLR 2021, MLILAB, KAIST AI
 
G. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AI
G. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AIG. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AI
G. Park, J.-Y. Yang, et. al., NeurIPS 2020, MLILAB, KAIST AI
 
I. Chung, AAAI 2020, MLILAB, KAIST AI
I. Chung, AAAI 2020, MLILAB, KAIST AII. Chung, AAAI 2020, MLILAB, KAIST AI
I. Chung, AAAI 2020, MLILAB, KAIST AI
 
H. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AIH. Shim, NeurIPS 2018, MLILAB, KAIST AI
H. Shim, NeurIPS 2018, MLILAB, KAIST AI
 

Recently uploaded

VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Christo Ananth
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Christo Ananth
 

Recently uploaded (20)

University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
 
UNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICS
UNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICSUNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICS
UNIT-IFLUID PROPERTIES & FLOW CHARACTERISTICS
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
 
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxBSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
 
NFPA 5000 2024 standard .
NFPA 5000 2024 standard                                  .NFPA 5000 2024 standard                                  .
NFPA 5000 2024 standard .
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
Vivazz, Mieres Social Housing Design Spain
Vivazz, Mieres Social Housing Design SpainVivazz, Mieres Social Housing Design Spain
Vivazz, Mieres Social Housing Design Spain
 
Online banking management system project.pdf
Online banking management system project.pdfOnline banking management system project.pdf
Online banking management system project.pdf
 
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar  ≼🔝 Delhi door step de...
Call Now ≽ 9953056974 ≼🔝 Call Girls In New Ashok Nagar ≼🔝 Delhi door step de...
 
chapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringchapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineering
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
 
Unit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdfUnit 1 - Soil Classification and Compaction.pdf
Unit 1 - Soil Classification and Compaction.pdf
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
The Most Attractive Pune Call Girls Manchar 8250192130 Will You Miss This Cha...
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 

Y. Jung, ICML 2023, MLILAB, KAISTAI

  • 1. Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation Yeonsung Jung, Hajin Shim, June Yong Yang, Eunho Yang Korea Advanced Institute of Science and Technology (KAIST) ICML 2023
  • 2. • Deep neural networks easily rely on the malignant biases as shortcuts. • Malignant bias • Colored MNIST: Digits (task) and Color (malignant bias) • Addressing bias problem is crucial in real-world applications. • Significant consequences for domains such as healthcare or autonomous driving. What is Debiasing? 2 [1] Lee et al., Learning Debiased Representation via Disentangled Feature Augmentation, NeurIPS’2021 Colored MNIST [1] Biased samples (Bias-aligned samples) Bias-free samples (Bias-conflicting samples)
  • 3. • Existing works focus on identifying and emphasizing handful bias-free samples. • Even though bias-aligned samples are the majority and also contain valuable task- related information, they are often underutilized or even discarded. • Also, previous methods easily break down in regimes where bias-free samples are scarce or absent. Motivation 3 Bias-aligned samples Bias-free samples ≪ (Minority) (Majority) < Previous >
  • 4. • Existing works focus on identifying and emphasizing handful bias-free samples. • Even though bias-aligned samples are the majority and also contain valuable task- related information, they are often underutilized or even discarded. • Also, previous methods easily break down in regimes where bias-free samples are scarce or absent. • Let’s focus on utilizing abundant bias-aligned samples. Motivation 4 Bias-aligned samples Bias-free samples < Ours > ≪ (Minority) (Majority)
  • 5. • Image translation models (e.g. CycleGAN[1], StarGAN[2]) render an image 𝑥 from a source domain 𝑦 to a target domain 𝑦!. • We hypothesize that in the case of biased dataset, the attributes representing the the target domain 𝒚! likely to be biased. Synthesizing Bias-frees Samples via Image Translation Models 5 [1] Zhu at al., Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, ICCV’2017 [2] Choi et al., StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation, CVPR’2018 Image 𝑥 Translation model Output Bias-aligned samples Generated Bias-free samples Target domain 𝑦!
  • 6. • We examine the behavior of the GAN-based images translation model, StarGAN, on biased datasets. • We observed that the domain discriminator of image translation models perceives the malignant bias as the representative trait of the class 𝑦. Image Translation Models Favor Malignant Bias. 6 Domain classification Real/Fake 1) Lead the discriminator to be biased Bias-transformed Biased sample Target class <Training StarGAN with biased dataset> Discriminator ! Generator " #! ~%
  • 7. • We examine the behavior of the GAN-based images translation model, StarGAN, on biased datasets. • We observed that the domain discriminator of image translation models perceives the malignant bias as the representative trait of the class 𝑦. • The accuracy of bias-aligned samples increases to nearly 100%. Image Translation Models Favor Malignant Bias. 7
  • 8. • We also observed that the biased domain classifier 𝐷"#$ induces a biased generator 𝐺 by optimizing the domain classification loss: Image Translation Models Favor Malignant Bias. 8 ℒ"#$ % = 𝔼(',))~𝒟,)!~𝒴[− log 𝐷"#$(𝑦! |𝐺 𝑥, 𝑦! )] Domain classification Real/Fake 1) Lead the discriminator to be biased Bias-transformed Biased sample Target class 2) Lead the generator to translate bias features <Training StarGAN with biased dataset> Discriminator ! Generator " #!~%
  • 9. • We also observed that the biased domain classifier 𝐷"#$ induces a biased generator 𝐺 by optimizing the domain classification loss: • Bias-translated images on various biased datasets. Image Translation Models Favor Malignant Bias. 9 ℒ"#$ % = 𝔼(',))~𝒟,)!~𝒴[− log 𝐷"#$(𝑦! |𝐺 𝑥, 𝑦! )]
  • 10. • Fighting Fire with Fire: Pitting one bias type against another via contrastive learning[1]. • Employing the bias-translation model as an augmentation method of contrastive learning. • By contrasting the bias-aligned sample and the bias-transformed view against each other, we can attenuate the bias while learning the task-related attributes. Contrastive Debiasing via Generative Bias-transformation (CDvG) 10 <Whole framework> ! "! #"~% &′ & (′ ( Maximize agreement by Contrastive loss Bias-transformed View Generation ##~% ℒ!" ℒ!# + Bias-transformed !′ Biased sample ! )! ~* Encoder + Pretrained , [1] Chen at al., A Simple Framework for Contrastive Learning of Visual Representations, ICML’2020
  • 11. • Quantitative results • Integration with the previous works which focus on bias-free samples (e.g. LfF). Experiments 11
  • 12. • Qualitative results • Visualization of learned representations using T-SNE on Colored MNIST • Visualization of Grad-CAM heatmaps on BFFHQ Experiments 12
  • 13. Thank you ! Any Questions ?