# Learning Debiased Representation via Disentangled Feature Augmentation

arXiv: https://arxiv.org/abs/2107.01372 · HTML: https://mlsanity.com/paper/2107.01372/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 3 Jul 2021.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [RUBi: Reducing Unimodal Biases in Visual Question Answering](https://mlsanity.com/paper/1906.10169/) (2019)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [REPAIR: Removing Representation Bias by Dataset Resampling](https://mlsanity.com/paper/1904.07911/) (2019)
- [Learning from Failure: Training Debiased Classifier from Biased Classifier](https://mlsanity.com/paper/2007.02561/) (2020)
- [Learning Robust Representations by Projecting Superficial Statistics Out](https://mlsanity.com/paper/1903.06256/) (2019)
- [Analyzing the Behavior of Visual Question Answering Models](https://mlsanity.com/paper/1606.07356/) (2016)
- [EnD: Entangling and Disentangling deep representations for bias correction](https://mlsanity.com/paper/2103.02023/) (2021)
- [FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders](https://mlsanity.com/paper/2103.06413/) (2021)
- [Automatic Shortcut Removal for Self-Supervised Representation Learning](https://mlsanity.com/paper/2002.08822/) (2020)
- [Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks](https://mlsanity.com/paper/2011.11486/) (2020)

## Built on by (most cited first, 30 of 116)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure](https://mlsanity.com/paper/2209.14107/) (2022)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [MEDFAIR: Benchmarking Fairness for Medical Imaging](https://mlsanity.com/paper/2210.01725/) (2022)
- [Learning Debiased Classifier with Biased Committee](https://mlsanity.com/paper/2206.10843/) (2022)
- [Discover and Mitigate Unknown Biases with Debiasing Alternate Networks](https://mlsanity.com/paper/2207.10077/) (2022)
- [Harnessing Out-Of-Distribution Examples via Augmenting Content and Style](https://mlsanity.com/paper/2207.03162/) (2022)
- [Does Invariant Graph Learning via Environment Augmentation Learn Invariance?](https://mlsanity.com/paper/2310.19035/) (2023)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Unbiased Supervised Contrastive Learning](https://mlsanity.com/paper/2211.05568/) (2022)
- [Core Knowledge Deficits in Multi-Modal Language Models](https://mlsanity.com/paper/2410.10855/) (2024)
- [Avoiding spurious correlations via logit correction](https://mlsanity.com/paper/2212.01433/) (2022)
- [FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification](https://mlsanity.com/paper/2207.10888/) (2022)
- [SelecMix: Debiased Learning by Contradicting-pair Sampling](https://mlsanity.com/paper/2211.02291/) (2022)
- [Mitigating Dataset Bias by Using Per-sample Gradient](https://mlsanity.com/paper/2205.15704/) (2022)
- [DAGAD: Data Augmentation for Graph Anomaly Detection](https://mlsanity.com/paper/2210.09766/) (2022)
- [Revisiting the Importance of Amplifying Bias for Debiasing](https://mlsanity.com/paper/2205.14594/) (2022)
- [Identifying Hard Noise in Long-Tailed Sample Distribution](https://mlsanity.com/paper/2207.13378/) (2022)
- [FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations](https://mlsanity.com/paper/2304.14252/) (2023)
- [A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation](https://mlsanity.com/paper/2410.19265/) (2024)
- [Training Debiased Subnetworks with Contrastive Weight Pruning](https://mlsanity.com/paper/2210.05247/) (2022)
- [Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods](https://mlsanity.com/paper/2208.00781/) (2022)
- [Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classification](https://mlsanity.com/paper/2203.09860/) (2022)
- [Equivariance and Invariance Inductive Bias for Learning from Insufficient Data](https://mlsanity.com/paper/2207.12258/) (2022)
- [Prefix Conditioning Unifies Language and Label Supervision](https://mlsanity.com/paper/2206.01125/) (2022)
- [SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems](https://mlsanity.com/paper/2308.00994/) (2023)
- [Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse](https://mlsanity.com/paper/2405.05587/) (2024)
- [General Debiasing for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2307.10511/) (2023)
- [Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement](https://mlsanity.com/paper/2311.15303/) (2023)

## Abstract (arXiv)

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability when evaluated on unbiased datasets. Existing approaches for debiasing often identify and emphasize those samples with no such correlation (i.e., bias-conflicting) without defining the bias type in advance. However, such bias-conflicting samples are significantly scarce in biased datasets, limiting the debiasing capability of these approaches. This paper first presents an empirical analysis revealing that training with "diverse" bias-conflicting samples beyond a given training set is crucial for debiasing as well as the generalization capability. Based on this observation, we propose a novel feature-level data augmentation technique in order to synthesize diverse bias-conflicting samples. To this end, our method learns the disentangled representation of (1) the intrinsic attributes (i.e., those inherently defining a certain class) and (2) bias attributes (i.e., peripheral attributes causing the bias), from a large number of bias-aligned samples, the bias attributes of which have strong correlation with the target variable. Using the disentangled representation, we synthesize bias-conflicting samples that contain the diverse intrinsic attributes of bias-aligned samples by swapping their latent features. By utilizing these diversified bias-conflicting features during the training, our approach achieves superior classification accuracy and debiasing results against the existing baselines on synthetic and real-world datasets.