mlsanityData to 7 Oct 2026

Component-Based Out-of-Distribution Detection

arXiv 2604.21546 ↗First posted 23 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Out-of-Distribution (OOD) detection requires sensitivity to subtle shifts without overreacting to natural In-Distribution (ID) diversity. However, from the viewpoint of detection granularity, global representation inevitably suppress local OOD cues, while patch-based methods are unstable due to entangled spurious-correlation and noise. And neither them is effective in detecting compositional OODs composed of valid ID components. Inspired by recognition-by-components theory, we present a training-free Component-Based OOD Detection (CoOD) framework that addresses the existing limitations by decomposing inputs into functional components. To instantiate CoOD, we derive Component Shift Score (CSS) to detect local appearance shifts, and Compositional Consistency Score (CCS) to identify cross-component compositional inconsistencies. Empirically, CoOD achieves consistent improvements on both coarse- and fine-grained OOD detection.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 53 references that are in the map. First posted on arXiv 23 Apr 2026.

Builds on

38 of 53 references.

References · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  5. 2013Describing Textures in the Wildcited by 2,110
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  8. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  9. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  10. 2017Dynamic Routing Between Capsulescited by 689
  11. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  12. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
26 more
  1. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  2. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  3. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 349
  4. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  5. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  6. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  7. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  8. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  9. 2022Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-trainingcited by 71
  10. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  11. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  12. 2023ID-like Prompt Learning for Few-Shot Out-of-Distribution Detectioncited by 42
  13. 2023Diversity-Measurable Anomaly Detectioncited by 41
  14. 2020Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusioncited by 38
  15. 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 30
  16. 2021Multi-scale Feature Learning Dynamics: Insights for Double Descentcited by 24
  17. 2022Recognizing Object by Components with Human Prior Knowledge Enhances Adversarial Robustness of Deep Neural Networkscited by 18
  18. 2023From Global to Local: Multi-scale Out-of-distribution Detectioncited by 18
  19. 2024Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detectioncited by 14
  20. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Modelscited by 13
  21. 2025Interpretable Image Classification via Non-parametric Part Prototype Learningcited by 11
  22. 2023Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fieldscited by 4
  23. 2025Revisiting Logit Distributions for Reliable Out-of-Distribution Detectioncited by 4
  24. 2023Image Background Serves as Good Proxy for Out-of-distribution Datacited by 3
  25. 2024DP-Net: Learning Discriminative Parts for image recognitioncited by 2
  26. 2025Delta Energy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalizationcited by 1

Built on by

Not cited yet.