# Identifying Spurious Correlations and Correcting them with an Explanation-based Learning

arXiv: https://arxiv.org/abs/2211.08285 · HTML: https://mlsanity.com/paper/2211.08285/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 55 references that are in the map.
- First posted on arXiv 15 Nov 2022.

## Builds on (most cited first, 24 of 24)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models](https://mlsanity.com/paper/1908.01224/) (2019)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)](https://mlsanity.com/paper/2005.13997/) (2020)
- [The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models](https://mlsanity.com/paper/2107.00758/) (2021)
- [Learn to Forget: Machine Unlearning via Neuron Masking](https://mlsanity.com/paper/2003.10933/) (2020)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [Understanding Failures of Deep Networks via Robust Feature Extraction](https://mlsanity.com/paper/2012.01750/) (2020)
- [Finding and Fixing Spurious Patterns with Explanations](https://mlsanity.com/paper/2106.02112/) (2021)
- [What does LIME really see in images?](https://mlsanity.com/paper/2102.06307/) (2021)
- ["Even if ..." -- Diverse Semifactual Explanations of Reject](https://mlsanity.com/paper/2207.01898/) (2022)
- [Impact of Feedback Type on Explanatory Interactive Learning](https://mlsanity.com/paper/2209.12476/) (2022)
- [Probabilistic Object Classification using CNN ML-MAP layers](https://mlsanity.com/paper/2005.14565/) (2020)
- [Optimising Knee Injury Detection with Spatial Attention and Validating Localisation Ability](https://mlsanity.com/paper/2108.08136/) (2021)

## Built on by (most cited first, 10 of 10)

- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation](https://mlsanity.com/paper/2307.07907/) (2023)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [Studying How to Efficiently and Effectively Guide Models with Explanations](https://mlsanity.com/paper/2303.11932/) (2023)
- [Unlearning Spurious Correlations in Chest X-ray Classification](https://mlsanity.com/paper/2308.01119/) (2023)
- [Learning from Exemplary Explanations](https://mlsanity.com/paper/2307.06026/) (2023)
- [Distance-Aware eXplanation Based Learning](https://mlsanity.com/paper/2309.05548/) (2023)
- [Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification](https://mlsanity.com/paper/2311.01655/) (2023)
- [Explainable Image Classification with Reduced Overconfidence for Tissue Characterisation](https://mlsanity.com/paper/2507.23709/) (2025)
- [eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts](https://mlsanity.com/paper/2605.06368/) (2026)

## Abstract (arXiv)

Identifying spurious correlations learned by a trained model is at the core of refining a trained model and building a trustworthy model. We present a simple method to identify spurious correlations that have been learned by a model trained for image classification problems. We apply image-level perturbations and monitor changes in certainties of predictions made using the trained model. We demonstrate this approach using an image classification dataset that contains images with synthetically generated spurious regions and show that the trained model was overdependent on spurious regions. Moreover, we remove the learned spurious correlations with an explanation based learning approach.