# ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations

arXiv: https://arxiv.org/abs/2403.13870 · HTML: https://mlsanity.com/paper/2403.13870/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Builds on (most cited first, 30 of 34)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering](https://mlsanity.com/paper/1811.03728/) (2018)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach](https://mlsanity.com/paper/1610.03425/) (2016)
- [Large-Scale Methods for Distributionally Robust Optimization](https://mlsanity.com/paper/2010.05893/) (2020)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [On Feature Learning in the Presence of Spurious Correlations](https://mlsanity.com/paper/2210.11369/) (2022)
- [Distributionally Robust Language Modeling](https://mlsanity.com/paper/1909.02060/) (2019)
- [Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation](https://mlsanity.com/paper/2204.02070/) (2022)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Places: An Image Database for Deep Scene Understanding](https://mlsanity.com/paper/1610.02055/) (2016)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Towards Best Practice in Explaining Neural Network Decisions with LRP](https://mlsanity.com/paper/1910.09840/) (2019)
- [MaskTune: Mitigating Spurious Correlations by Forcing to Explore](https://mlsanity.com/paper/2210.00055/) (2022)
- [Examining and Combating Spurious Features under Distribution Shift](https://mlsanity.com/paper/2106.07171/) (2021)
- [Distributionally Robust Losses for Latent Covariate Mixtures](https://mlsanity.com/paper/2007.13982/) (2020)
- [Clustering without Over-Representation](https://mlsanity.com/paper/1905.12753/) (2019)
- [On the cost of essentially fair clusterings](https://mlsanity.com/paper/1811.10319/) (2018)
- [Unsupervised Learning of Debiased Representations with Pseudo-Attributes](https://mlsanity.com/paper/2108.02943/) (2021)

## Built on by (most cited first, 8 of 8)

- [Debugging Concept Bottleneck Models through Removal and Retraining](https://mlsanity.com/paper/2509.21385/) (2025)
- [Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization](https://mlsanity.com/paper/2501.14182/) (2025)
- [Fine-Grained Class-Conditional Distribution Balancing for Debiased Learning](https://mlsanity.com/paper/2505.06831/) (2025)
- [Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement](https://mlsanity.com/paper/2606.24161/) (2026)
- [Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions](https://mlsanity.com/paper/2605.28780/) (2026)
- [Fairness Beyond Demographics: Optimizing Performance Across Appearance-Based Hidden Cohorts in Medical Imaging](https://mlsanity.com/paper/2605.29827/) (2026)
- [Discovering Latent Groups for Robust Classification](https://mlsanity.com/paper/2606.23609/) (2026)
- [Beyond Metadata: CAPRA for Hidden Subgroup Analysis under Missing Metadata in Medical Imaging](https://mlsanity.com/paper/2607.09102/) (2026)

## Abstract (arXiv)

Group robustness strategies aim to mitigate learned biases in deep learning models that arise from spurious correlations present in their training datasets. However, most existing methods rely on the access to the label distribution of the groups, which is time-consuming and expensive to obtain. As a result, unsupervised group robustness strategies are sought. Based on the insight that a trained model's classification strategies can be inferred accurately based on explainability heatmaps, we introduce ExMap, an unsupervised two stage mechanism designed to enhance group robustness in traditional classifiers. ExMap utilizes a clustering module to infer pseudo-labels based on a model's explainability heatmaps, which are then used during training in lieu of actual labels. Our empirical studies validate the efficacy of ExMap - We demonstrate that it bridges the performance gap with its supervised counterparts and outperforms existing partially supervised and unsupervised methods. Additionally, ExMap can be seamlessly integrated with existing group robustness learning strategies. Finally, we demonstrate its potential in tackling the emerging issue of multiple shortcut mitigationfootnoteCode available at urlhttps://github.com/rwchakra/exmap.