mlsanityData to 14 Oct 2026

Out-of-Distribution Detection Without Class Labels

arXiv 2112.07662 ↗First posted 14 Dec 2021cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution detection seeks to identify novelties, samples that deviate from the norm. The task has been found to be quite challenging, particularly in the case where the normal data distribution consists of multiple semantic classes (e.g., multiple object categories). To overcome this challenge, current approaches require manual labeling of the normal images provided during training. In this work, we tackle multi-class novelty detection without class labels. Our simple but effective solution consists of two stages: we first discover "pseudo-class" labels using unsupervised clustering. Then using these pseudo-class labels, we are able to use standard supervised out-of-distribution detection methods. We verify the performance of our method by a favorable comparison to the state-of-the-art, and provide extensive analysis and ablations.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 14 Dec 2021.

Builds on

30 of 51 references.

References · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  6. 2013Describing Textures in the Wildcited by 2,125
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  10. 2019Big Transfer (BiT): General Visual Representation Learningcited by 769
  11. 2021Merging Models with Fisher-Weighted Averagingcited by 621
  12. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
18 more
  1. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  2. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
  3. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  4. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  5. 2020SCAN: Learning to Classify Images without Labelscited by 352
  6. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  7. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  8. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  9. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  10. 2020Classification-Based Anomaly Detection for General Datacited by 211
  11. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  12. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  13. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  14. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  15. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  16. 2018Learning Deep Features for One-Class Classificationcited by 76
  17. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  18. 2021Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representationscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2024Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detectioncited by 15
  2. 2023Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localizationcited by 10
  3. 2023Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detectioncited by 0
  4. 2023CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classificationcited by 0
  5. 2026Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomaliescited by 0