# Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair

arXiv: https://arxiv.org/abs/2404.19250 · HTML: https://mlsanity.com/paper/2404.19250/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 30 Apr 2024.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [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)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (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)
- [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)
- [Learning Debiased Representation via Disentangled Feature Augmentation](https://mlsanity.com/paper/2107.01372/) (2021)
- [EnD: Entangling and Disentangling deep representations for bias correction](https://mlsanity.com/paper/2103.02023/) (2021)
- [BiaSwap: Removing dataset bias with bias-tailored swapping augmentation](https://mlsanity.com/paper/2108.10008/) (2021)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [SelecMix: Debiased Learning by Contradicting-pair Sampling](https://mlsanity.com/paper/2211.02291/) (2022)
- [Revisiting the Importance of Amplifying Bias for Debiasing](https://mlsanity.com/paper/2205.14594/) (2022)
- [Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks](https://mlsanity.com/paper/2011.11486/) (2020)
- [Training Debiased Subnetworks with Contrastive Weight Pruning](https://mlsanity.com/paper/2210.05247/) (2022)
- [DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation](https://mlsanity.com/paper/2209.06357/) (2022)

## Built on by (most cited first, 4 of 4)

- [Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing](https://mlsanity.com/paper/2502.09564/) (2025)
- [BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers](https://mlsanity.com/paper/2605.28450/) (2026)
- [Towards Real-world Debiasing: Rethinking Evaluation, Challenge, and Solution](https://mlsanity.com/paper/2405.15240/) (2024)
- [BLADE: Bias-Linked Adaptive DEbiasing](https://mlsanity.com/paper/2510.04174/) (2025)

## Abstract (arXiv)

In the image classification task, deep neural networks frequently rely on bias attributes that are spuriously correlated with a target class in the presence of dataset bias, resulting in degraded performance when applied to data without bias attributes. The task of debiasing aims to compel classifiers to learn intrinsic attributes that inherently define a target class rather than focusing on bias attributes. While recent approaches mainly focus on emphasizing the learning of data samples without bias attributes (i.e., bias-conflicting samples) compared to samples with bias attributes (i.e., bias-aligned samples), they fall short of directly guiding models where to focus for learning intrinsic features. To address this limitation, this paper proposes a method that provides the model with explicit spatial guidance that indicates the region of intrinsic features. We first identify the intrinsic features by investigating the class-discerning common features between a bias-aligned (BA) sample and a bias-conflicting (BC) sample (i.e., bias-contrastive pair). Next, we enhance the intrinsic features in the BA sample that are relatively under-exploited for prediction compared to the BC sample. To construct the bias-contrastive pair without using bias information, we introduce a bias-negative score that distinguishes BC samples from BA samples employing a biased model. The experiments demonstrate that our method achieves state-of-the-art performance on synthetic and real-world datasets with various levels of bias severity.