# A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others

arXiv: https://arxiv.org/abs/2212.04825 · HTML: https://mlsanity.com/paper/2212.04825/

## Key facts

- Cited by 85 papers in the map (data through 14 Oct 2026).
- Builds on 82 of its 105 references that are in the map.
- First posted on arXiv 9 Dec 2022.

## Builds on (most cited first, 30 of 82)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)

## Built on by (most cited first, 30 of 85)

- [Change is Hard: A Closer Look at Subpopulation Shift](https://mlsanity.com/paper/2302.12254/) (2023)
- [Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias](https://mlsanity.com/paper/2305.18761/) (2023)
- [Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases](https://mlsanity.com/paper/2303.05470/) (2023)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Overwriting Pretrained Bias with Finetuning Data](https://mlsanity.com/paper/2303.06167/) (2023)
- [Labeling Neural Representations with Inverse Recognition](https://mlsanity.com/paper/2311.13594/) (2023)
- [Identifying Implicit Social Biases in Vision-Language Models](https://mlsanity.com/paper/2411.00997/) (2024)
- [From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space](https://mlsanity.com/paper/2308.09437/) (2023)
- [Investigating the Benefits of Projection Head for Representation Learning](https://mlsanity.com/paper/2403.11391/) (2024)
- [BendVLM: Test-Time Debiasing of Vision-Language Embeddings](https://mlsanity.com/paper/2411.04420/) (2024)
- [Improving Domain Generalization with Domain Relations](https://mlsanity.com/paper/2302.02609/) (2023)
- [ImageNot: A contrast with ImageNet preserves model rankings](https://mlsanity.com/paper/2404.02112/) (2024)
- [Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods](https://mlsanity.com/paper/2406.12142/) (2024)
- [Intermediate Layer Classifiers for OOD generalization](https://mlsanity.com/paper/2504.05461/) (2025)
- [Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations?](https://mlsanity.com/paper/2506.18322/) (2025)
- [Effective Robustness against Natural Distribution Shifts for Models with Different Training Data](https://mlsanity.com/paper/2302.01381/) (2023)
- [Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?](https://mlsanity.com/paper/2307.13136/) (2023)
- [From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition](https://mlsanity.com/paper/2308.04553/) (2023)
- [Unsupervised Concept Discovery Mitigates Spurious Correlations](https://mlsanity.com/paper/2402.13368/) (2024)
- [Discover and Mitigate Multiple Biased Subgroups in Image Classifiers](https://mlsanity.com/paper/2403.12777/) (2024)
- [Are We Done with Object-Centric Learning?](https://mlsanity.com/paper/2504.07092/) (2025)
- [Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features](https://mlsanity.com/paper/2302.05441/) (2023)
- [Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms](https://mlsanity.com/paper/2306.08167/) (2023)
- [What Makes ImageNet Look Unlike LAION](https://mlsanity.com/paper/2306.15769/) (2023)
- [Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data](https://mlsanity.com/paper/2307.01088/) (2023)
- [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)
- [LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers](https://mlsanity.com/paper/2408.07832/) (2024)
- [Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation](https://mlsanity.com/paper/2607.21973/) (2026)

## Abstract (arXiv)

Machine learning models have been found to learn shortcuts -- unintended decision rules that are unable to generalize -- undermining models' reliability. Previous works address this problem under the tenuous assumption that only a single shortcut exists in the training data. Real-world images are rife with multiple visual cues from background to texture. Key to advancing the reliability of vision systems is understanding whether existing methods can overcome multiple shortcuts or struggle in a Whac-A-Mole game, i.e., where mitigating one shortcut amplifies reliance on others. To address this shortcoming, we propose two benchmarks: 1) UrbanCars, a dataset with precisely controlled spurious cues, and 2) ImageNet-W, an evaluation set based on ImageNet for watermark, a shortcut we discovered affects nearly every modern vision model. Along with texture and background, ImageNet-W allows us to study multiple shortcuts emerging from training on natural images. We find computer vision models, including large foundation models -- regardless of training set, architecture, and supervision -- struggle when multiple shortcuts are present. Even methods explicitly designed to combat shortcuts struggle in a Whac-A-Mole dilemma. To tackle this challenge, we propose Last Layer Ensemble, a simple-yet-effective method to mitigate multiple shortcuts without Whac-A-Mole behavior. Our results surface multi-shortcut mitigation as an overlooked challenge critical to advancing the reliability of vision systems. The datasets and code are released: https://github.com/facebookresearch/Whac-A-Mole.