# Towards Robust Classification Model by Counterfactual and Invariant Data Generation

arXiv: https://arxiv.org/abs/2106.01127 · HTML: https://mlsanity.com/paper/2106.01127/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 42 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 30 of 36)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [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)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (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)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Counterfactual Samples Synthesizing for Robust Visual Question Answering](https://mlsanity.com/paper/2003.06576/) (2020)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [Analyzing the Behavior of Visual Question Answering Models](https://mlsanity.com/paper/1606.07356/) (2016)
- [Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing](https://mlsanity.com/paper/1912.07538/) (2019)
- [Hierarchical interpretations for neural network predictions](https://mlsanity.com/paper/1806.05337/) (2018)
- [Deriving Machine Attention from Human Rationales](https://mlsanity.com/paper/1808.09367/) (2018)
- [Embedding Human Knowledge into Deep Neural Network via Attention Map](https://mlsanity.com/paper/1905.03540/) (2019)
- [Improving performance of deep learning models with axiomatic attribution priors and expected gradients](https://mlsanity.com/paper/1906.10670/) (2019)
- [(De)Constructing Bias on Skin Lesion Datasets](https://mlsanity.com/paper/1904.08818/) (2019)

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

- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes](https://mlsanity.com/paper/2201.10766/) (2022)
- [Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation](https://mlsanity.com/paper/2312.14223/) (2023)
- [GaitGCI: Generative Counterfactual Intervention for Gait Recognition](https://mlsanity.com/paper/2306.03428/) (2023)
- [Understanding Rare Spurious Correlations in Neural Networks](https://mlsanity.com/paper/2202.05189/) (2022)
- [Core Risk Minimization using Salient ImageNet](https://mlsanity.com/paper/2203.15566/) (2022)
- [Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective](https://mlsanity.com/paper/2208.12681/) (2022)
- [Causal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection](https://mlsanity.com/paper/2403.01300/) (2024)
- [Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis](https://mlsanity.com/paper/2412.20651/) (2024)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features](https://mlsanity.com/paper/2305.12100/) (2023)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective](https://mlsanity.com/paper/2410.12816/) (2024)
- [Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization](https://mlsanity.com/paper/2502.01347/) (2025)
- [CaRT: Teaching LLM Agents to Know When They Know Enough](https://mlsanity.com/paper/2510.08517/) (2025)
- [Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification](https://mlsanity.com/paper/2307.04343/) (2023)
- [Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training](https://mlsanity.com/paper/2605.11134/) (2026)
- [AutoCAD: Automatically Generating Counterfactuals for Mitigating Shortcut Learning](https://mlsanity.com/paper/2211.16202/) (2022)
- [Sebra: Debiasing Through Self-Guided Bias Ranking](https://mlsanity.com/paper/2501.18277/) (2025)
- [Efficient Classification with Counterfactual Reasoning and Active Learning](https://mlsanity.com/paper/2207.12086/) (2022)
- [Implicit Counterfactual Data Augmentation for Robust Learning](https://mlsanity.com/paper/2304.13431/) (2023)
- [Genetic InfoMax: Exploring Mutual Information Maximization in High-Dimensional Imaging Genetics Studies](https://mlsanity.com/paper/2309.15132/) (2023)
- [Automated Background Swapping for Robustness against Spurious Backgrounds](https://mlsanity.com/paper/2606.32018/) (2026)
- [Impact of Label Types on Training SWIN Models with Overhead Imagery](https://mlsanity.com/paper/2310.07572/) (2023)
- [Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality](https://mlsanity.com/paper/2406.11501/) (2024)
- [Mitigating Spurious Correlations with Causal Logit Perturbation](https://mlsanity.com/paper/2505.15246/) (2025)
- [Shortcut Invariance: Targeted Jacobian Regularization in Disentangled Latent Space](https://mlsanity.com/paper/2511.19525/) (2025)
- [Causal Transfer in Medical Image Analysis](https://mlsanity.com/paper/2603.24388/) (2026)
- [Concept-based Visual Counterfactual Explanations with Diffusion Models](https://mlsanity.com/paper/2607.22544/) (2026)
- [When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models](https://mlsanity.com/paper/2609.39971/) (2026)

## Abstract (arXiv)

Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occurs when some features correlate with labels but are not causal; relying on such features prevents models from generalizing to unseen environments where such correlations break. In this work, we focus on image classification and propose two data generation processes to reduce spuriousness. Given human annotations of the subset of the features responsible (causal) for the labels (e.g. bounding boxes), we modify this causal set to generate a surrogate image that no longer has the same label (i.e. a counterfactual image). We also alter non-causal features to generate images still recognized as the original labels, which helps to learn a model invariant to these features. In several challenging datasets, our data generations outperform state-of-the-art methods in accuracy when spurious correlations break, and increase the saliency focus on causal features providing better explanations.