mlsanityData to 14 Oct 2026

Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!

arXiv 2210.03103 ↗First posted 6 Oct 2022cs.CV cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We introduce a formalization and benchmark for the unsupervised anomaly detection task in the distribution-shift scenario. Our work builds upon the iWildCam dataset, and, to the best of our knowledge, we are the first to propose such an approach for visual data. We empirically validate that environment-aware methods perform better in such cases when compared with the basic Empirical Risk Minimization (ERM). We next propose an extension for generating positive samples for contrastive methods that considers the environment labels when training, improving the ERM baseline score by 8.7%.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 31 of its 57 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

31 of 57 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  7. 2019Invariant Risk Minimizationcited by 1,854
  8. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  9. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  11. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  12. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
19 more
  1. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  2. 2018Recognition in Terra Incognitacited by 658
  3. 2013Domain Generalization via Invariant Feature Representationcited by 623
  4. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  5. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  6. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  7. 2021Gradient Matching for Domain Generalizationcited by 258
  8. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 230
  9. 2019PyOD: A Python Toolbox for Scalable Outlier Detectioncited by 222
  10. 2021Towards Causal Representation Learningcited by 209
  11. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  12. 2020Representation Learning via Invariant Causal Mechanismscited by 199
  13. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  14. 2021Disparities in Dermatology AI: Assessments Using Diverse Clinical Imagescited by 134
  15. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 93
  16. 2020The iWildCam 2020 Competition Datasetcited by 86
  17. 2022MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflictscited by 81
  18. 2017Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learningcited by 63
  19. 2022AnoShift: A Distribution Shift Benchmark for Unsupervised Anomaly Detectioncited by 11

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023Invariant Anomaly Detection under Distribution Shifts: A Causal Perspectivecited by 8
  2. 2023Robust Novelty Detection through Style-Conscious Feature Rankingcited by 1
  3. 2023Environment-biased Feature Ranking for Novelty Detection Robustnesscited by 0