# The Clever Hans Effect in Unsupervised Learning

arXiv: https://arxiv.org/abs/2408.08041 · HTML: https://mlsanity.com/paper/2408.08041/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 96 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [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)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images](https://mlsanity.com/paper/2003.09871/) (2020)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies](https://mlsanity.com/paper/2303.14535/) (2023)
- [Deep Learning for Anomaly Detection: A Review](https://mlsanity.com/paper/2007.02500/) (2020)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [Frequency Bias in Neural Networks for Input of Non-Uniform Density](https://mlsanity.com/paper/2003.04560/) (2020)
- [Higher-Order Explanations of Graph Neural Networks via Relevant Walks](https://mlsanity.com/paper/2006.03589/) (2020)
- [Intriguing Properties of Contrastive Losses](https://mlsanity.com/paper/2011.02803/) (2020)
- [Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection](https://mlsanity.com/paper/2005.14140/) (2020)
- [Can contrastive learning avoid shortcut solutions?](https://mlsanity.com/paper/2106.11230/) (2021)
- [COVID-19 Image Data Collection: Prospective Predictions Are the Future](https://mlsanity.com/paper/2006.11988/) (2020)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)

## Built on by (most cited first, 24 of 24)

- [Mechanistic understanding and validation of large AI models with SemanticLens](https://mlsanity.com/paper/2501.05398/) (2025)
- [Do Histopathological Foundation Models Eliminate Batch Effects? A Comparative Study](https://mlsanity.com/paper/2411.05489/) (2024)
- [Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features](https://mlsanity.com/paper/2408.17198/) (2024)
- [Opportunities and limitations of explaining quantum machine learning](https://mlsanity.com/paper/2412.14753/) (2024)
- [Towards Desiderata-Driven Design of Visual Counterfactual Explainers](https://mlsanity.com/paper/2506.14698/) (2025)
- [MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification](https://mlsanity.com/paper/2506.17140/) (2025)
- [Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples](https://mlsanity.com/paper/2510.17524/) (2025)
- [Atlas 2 -- Foundation models for clinical deployment](https://mlsanity.com/paper/2601.05148/) (2026)
- [Position: We Need An Algorithmic Understanding of Generative AI](https://mlsanity.com/paper/2507.07544/) (2025)
- [Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Models](https://mlsanity.com/paper/2601.21851/) (2026)
- [Model Science: getting serious about verification, explanation and control of AI systems](https://mlsanity.com/paper/2508.20040/) (2025)
- [Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena](https://mlsanity.com/paper/2505.06123/) (2025)
- [Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces](https://mlsanity.com/paper/2601.05913/) (2026)
- [Where Not to Learn: Prior-Aligned Training with Subset-based Attribution Constraints](https://mlsanity.com/paper/2602.07008/) (2026)
- [Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology](https://mlsanity.com/paper/2603.08328/) (2026)
- [Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures](https://mlsanity.com/paper/2606.00557/) (2026)
- [Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion Recognition](https://mlsanity.com/paper/2506.19079/) (2025)
- [Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures](https://mlsanity.com/paper/2508.03913/) (2025)
- [Stable but Wrong: When Learning Stabilizes Away from the Truth](https://mlsanity.com/paper/2603.21491/) (2026)
- [Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology](https://mlsanity.com/paper/2606.06224/) (2026)
- [Explaining Temporal Graph Neural Networks via Feature-induced Information Flow](https://mlsanity.com/paper/2606.27201/) (2026)
- [Position: Reasoning is a Learnable Rule-Based Process](https://mlsanity.com/paper/2608.12325/) (2026)
- [HERO: Histology Encoder for Robust Representation in Oncology](https://mlsanity.com/paper/2609.35943/) (2026)
- [Towards Fast and Disentangled Counterfactuals for Visual Foundation Models](https://mlsanity.com/paper/2610.00895/) (2026)

## Abstract (arXiv)

Unsupervised learning has become an essential building block of AI systems. The representations it produces, e.g. in foundation models, are critical to a wide variety of downstream applications. It is therefore important to carefully examine unsupervised models to ensure not only that they produce accurate predictions, but also that these predictions are not "right for the wrong reasons", the so-called Clever Hans (CH) effect. Using specially developed Explainable AI techniques, we show for the first time that CH effects are widespread in unsupervised learning. Our empirical findings are enriched by theoretical insights, which interestingly point to inductive biases in the unsupervised learning machine as a primary source of CH effects. Overall, our work sheds light on unexplored risks associated with practical applications of unsupervised learning and suggests ways to make unsupervised learning more robust.