# MaskTune: Mitigating Spurious Correlations by Forcing to Explore

arXiv: https://arxiv.org/abs/2210.00055 · HTML: https://mlsanity.com/paper/2210.00055/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 67 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 30 of 37)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [The Marginal Value of Adaptive Gradient Methods in Machine Learning](https://mlsanity.com/paper/1705.08292/) (2017)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [SGD on Neural Networks Learns Functions of Increasing Complexity](https://mlsanity.com/paper/1905.11604/) (2019)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)
- [Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach](https://mlsanity.com/paper/1610.03425/) (2016)
- [Deep learning generalizes because the parameter-function map is biased towards simple functions](https://mlsanity.com/paper/1805.08522/) (2018)
- [Large-Scale Methods for Distributionally Robust Optimization](https://mlsanity.com/paper/2010.05893/) (2020)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [Adversarial Training Can Hurt Generalization](https://mlsanity.com/paper/1906.06032/) (2019)
- [Counterfactual Generative Networks](https://mlsanity.com/paper/2101.06046/) (2021)
- [Deep Gamblers: Learning to Abstain with Portfolio Theory](https://mlsanity.com/paper/1907.00208/) (2019)
- [Self-training Avoids Using Spurious Features Under Domain Shift](https://mlsanity.com/paper/2006.10032/) (2020)
- [Diversify and Disambiguate: Learning From Underspecified Data](https://mlsanity.com/paper/2202.03418/) (2022)
- [Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately](https://mlsanity.com/paper/2012.04104/) (2020)

## Built on by (most cited first, 30 of 66)

- [Towards Last-layer Retraining for Group Robustness with Fewer Annotations](https://mlsanity.com/paper/2309.08534/) (2023)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning](https://mlsanity.com/paper/2507.16795/) (2025)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations](https://mlsanity.com/paper/2403.07241/) (2024)
- [Group Robust Classification Without Any Group Information](https://mlsanity.com/paper/2310.18555/) (2023)
- [Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation](https://mlsanity.com/paper/2402.18919/) (2024)
- [Studying How to Efficiently and Effectively Guide Models with Explanations](https://mlsanity.com/paper/2303.11932/) (2023)
- [B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable](https://mlsanity.com/paper/2411.00715/) (2024)
- [Unsupervised Concept Discovery Mitigates Spurious Correlations](https://mlsanity.com/paper/2402.13368/) (2024)
- [Are We Done with Object-Centric Learning?](https://mlsanity.com/paper/2504.07092/) (2025)
- [Invariant Learning via Diffusion Dreamed Distribution Shifts](https://mlsanity.com/paper/2211.10370/) (2022)
- [Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation](https://mlsanity.com/paper/2405.03649/) (2024)
- [Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning](https://mlsanity.com/paper/2405.20439/) (2024)
- [Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness](https://mlsanity.com/paper/2503.09487/) (2025)
- [Towards Improved Input Masking for Convolutional Neural Networks](https://mlsanity.com/paper/2211.14646/) (2022)
- [Clarify: Improving Model Robustness With Natural Language Corrections](https://mlsanity.com/paper/2402.03715/) (2024)
- [ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations](https://mlsanity.com/paper/2403.13870/) (2024)
- [Efficient Bias Mitigation Without Privileged Information](https://mlsanity.com/paper/2409.17691/) (2024)
- [Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets](https://mlsanity.com/paper/2510.02818/) (2025)
- [Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness](https://mlsanity.com/paper/2310.06161/) (2023)
- [Spuriousness-Aware Meta-Learning for Learning Robust Classifiers](https://mlsanity.com/paper/2406.10742/) (2024)
- [Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenario](https://mlsanity.com/paper/2410.04740/) (2024)
- [The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations](https://mlsanity.com/paper/2407.13957/) (2024)
- [Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers](https://mlsanity.com/paper/2501.00942/) (2025)
- [DDB: Diffusion Driven Balancing to Address Spurious Correlations](https://mlsanity.com/paper/2503.17226/) (2025)
- [ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations](https://mlsanity.com/paper/2308.10103/) (2023)
- [Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment](https://mlsanity.com/paper/2408.06079/) (2024)
- [Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair](https://mlsanity.com/paper/2404.19250/) (2024)
- [Gradient Extrapolation for Debiased Representation Learning](https://mlsanity.com/paper/2503.13236/) (2025)

## Abstract (arXiv)

A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features. This work proposes MaskTune, a masking strategy that prevents over-reliance on spurious (or a limited number of) features. MaskTune forces the trained model to explore new features during a single epoch finetuning by masking previously discovered features. MaskTune, unlike earlier approaches for mitigating shortcut learning, does not require any supervision, such as annotating spurious features or labels for subgroup samples in a dataset. Our empirical results on biased MNIST, CelebA, Waterbirds, and ImagenNet-9L datasets show that MaskTune is effective on tasks that often suffer from the existence of spurious correlations. Finally, we show that MaskTune outperforms or achieves similar performance to the competing methods when applied to the selective classification (classification with rejection option) task. Code for MaskTune is available at https://github.com/aliasgharkhani/Masktune.