mlsanityData to 14 Oct 2026

SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation

arXiv 2406.12629 ↗First posted 18 Jun 2024cs.CL cs.AI cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is crucial for the safe deployment of neural networks. Existing CLIP-based approaches perform OOD detection by devising novel scoring functions or sophisticated fine-tuning methods. In this work, we propose SeTAR, a novel, training-free OOD detection method that leverages selective low-rank approximation of weight matrices in vision-language and vision-only models. SeTAR enhances OOD detection via post-hoc modification of the model's weight matrices using a simple greedy search algorithm. Based on SeTAR, we further propose SeTAR+FT, a fine-tuning extension optimizing model performance for OOD detection tasks. Extensive evaluations on ImageNet1K and Pascal-VOC benchmarks show SeTAR's superior performance, reducing the relatively false positive rate by up to 18.95% and 36.80% compared to zero-shot and fine-tuning baselines. Ablation studies further validate SeTAR's effectiveness, robustness, and generalizability across different model backbones. Our work offers a scalable, efficient solution for OOD detection, setting a new state-of-the-art in this area.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 44 of its 62 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

44 of 62 references.

References · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  8. 2013Describing Textures in the Wildcited by 2,125
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  12. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,274
32 more
  1. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  6. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  7. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  8. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 294
  9. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  10. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  11. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  12. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  13. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  14. 2023Non-Parametric Outlier Synthesiscited by 129
  15. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  16. 2023The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reductioncited by 123
  17. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  18. 2021Can multi-label classification networks know what they don't know?cited by 100
  19. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 71
  20. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  21. 2019Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobiancited by 67
  22. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  23. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  24. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  25. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  26. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  27. 2019Out-of-Domain Detection for Low-Resource Text Classification Taskscited by 36
  28. 2021Unsupervised Out-of-Domain Detection via Pre-trained Transformerscited by 31
  29. 2021Uncertainty-Aware Reliable Text Classificationcited by 23
  30. 2023Exploring Large Language Models for Multi-Modal Out-of-Distribution Detectioncited by 13
  31. 2024Energy-based Hopfield Boosting for Out-of-Distribution Detectioncited by 9
  32. 2024Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspectivecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 3.

10 papers.

  1. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  2. 2025RL Fine-Tuning Heals OOD Forgetting in SFTcited by 31
  3. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  4. 2025Unveiling Over-Memorization in Finetuning LLMs for Reasoning Taskscited by 11
  5. 2025Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Surveycited by 6
  6. 2025Out-of-Distribution Detection using Synthetic Data Generationcited by 4
  7. 2025GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detectioncited by 2
  8. 2026GP-Adapter: Gaussian Process CLIP-Adapter for Few-Shot Out-of-Distribution Detectioncited by 0
  9. 2026Not All Layers Are Equal: Dynamic Layer Routing for Reliable CLIP OOD Detectioncited by 0
  10. 2026ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detectioncited by 0