mlsanityData to 14 Oct 2026

Environment-biased Feature Ranking for Novelty Detection Robustness

arXiv 2309.12301 ↗First posted 21 Sep 2023cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We tackle the problem of robust novelty detection, where we aim to detect novelties in terms of semantic content while being invariant to changes in other, irrelevant factors. Specifically, we operate in a setup with multiple environments, where we determine the set of features that are associated more with the environments, rather than to the content relevant for the task. Thus, we propose a method that starts with a pretrained embedding and a multi-env setup and manages to rank the features based on their environment-focus. First, we compute a per-feature score based on the feature distribution variance between envs. Next, we show that by dropping the highly scored ones, we manage to remove spurious correlations and improve the overall performance by up to 6%, both in covariance and sub-population shift cases, both for a real and a synthetic benchmark, that we introduce for this task.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 21 Sep 2023.

Builds on

26 of 37 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  4. 2019Invariant Risk Minimizationcited by 1,854
  5. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  6. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  7. 2021Domain Generalization: A Surveycited by 764
  8. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  9. 2018Recognition in Terra Incognitacited by 658
  10. 2013Domain Generalization via Invariant Feature Representationcited by 623
  11. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  12. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
14 more
  1. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  2. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  3. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  4. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 381
  5. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  6. 2019PyOD: A Python Toolbox for Scalable Outlier Detectioncited by 222
  7. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  8. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  9. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  10. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  11. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 71
  12. 2019Detecting semantic anomaliescited by 50
  13. 2022Provable Domain Generalization via Invariant-Feature Subspace Recoverycited by 32
  14. 2022Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!cited by 3

Built on by

Not cited yet.