mlsanityData to 7 Oct 2026

Shortcut Detection with Variational Autoencoders

arXiv 2302.04246 ↗First posted 8 Feb 2023cs.LG cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

For real-world applications of machine learning (ML), it is essential that models make predictions based on well-generalizing features rather than spurious correlations in the data. The identification of such spurious correlations, also known as shortcuts, is a challenging problem and has so far been scarcely addressed. In this work, we present a novel approach to detect shortcuts in image and audio datasets by leveraging variational autoencoders (VAEs). The disentanglement of features in the latent space of VAEs allows us to discover feature-target correlations in datasets and semi-automatically evaluate them for ML shortcuts. We demonstrate the applicability of our method on several real-world datasets and identify shortcuts that have not been discovered before.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 58 references that are in the map. First posted on arXiv 8 Feb 2023.

Builds on

33 of 58 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  7. 2019Invariant Risk Minimizationcited by 1,832
  8. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  9. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  10. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  11. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  12. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
21 more
  1. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  2. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  3. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  4. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  5. 2020Backdoor Learning: A Surveycited by 412
  6. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  8. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 342
  9. 2018Adversarial Attacks and Defences: A Surveycited by 259
  10. 2019Diagnosing and Enhancing VAE Modelscited by 192
  11. 2022Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlationscited by 171
  12. 2018Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objectscited by 143
  13. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  14. 2020COVID-19 Image Data Collectioncited by 100
  15. 2020COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Imagescited by 60
  16. 2018Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentationcited by 49
  17. 2020Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detectioncited by 46
  18. 2021Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?cited by 36
  19. 2022CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGANcited by 25
  20. 2022Chroma-VAE: Mitigating Shortcut Learning with Generative Classifierscited by 17
  21. 2016Improving Weakly-Supervised Object Localization By Micro-Annotationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 2; 2026: 1.

5 papers.

  1. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  2. 2024Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigationcited by 22
  3. 2025Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformerscited by 6
  4. 2026Bias in the Shadows: Explore Shortcuts in Encrypted Network Traffic Classificationcited by 1
  5. 2025Shortcut Invariance: Targeted Jacobian Regularization in Disentangled Latent Spacecited by 0