mlsanityData to 7 Oct 2026

Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detection

arXiv 2312.01732 ↗First posted 4 Dec 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Full-spectrum out-of-distribution (F-OOD) detection aims to accurately recognize in-distribution (ID) samples while encountering semantic and covariate shifts simultaneously. However, existing out-of-distribution (OOD) detectors tend to overfit the covariance information and ignore intrinsic semantic correlation, inadequate for adapting to complex domain transformations. To address this issue, we propose a Likelihood-Aware Semantic Alignment (LSA) framework to promote the image-text correspondence into semantically high-likelihood regions. LSA consists of an offline Gaussian sampling strategy which efficiently samples semantic-relevant visual embeddings from the class-conditional Gaussian distribution, and a bidirectional prompt customization mechanism that adjusts both ID-related and negative context for discriminative ID/OOD boundary. Extensive experiments demonstrate the remarkable OOD detection performance of our proposed LSA especially on the intractable Near-OOD setting, surpassing existing methods by a margin of 15.26% and 18.88% on two F-OOD benchmarks, respectively.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 50 of its 58 references that are in the map. First posted on arXiv 4 Dec 2023.

Builds on

50 of 58 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023Segment Anythingcited by 8,158
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  8. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  11. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
38 more
  1. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  2. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  3. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  4. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  5. 2019How Can We Know What Language Models Know?cited by 953
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  8. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  9. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  10. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  11. 2021Extract Free Dense Labels from CLIPcited by 580
  12. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  13. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 560
  14. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  15. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  16. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  17. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  18. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  19. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  20. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  21. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  22. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  23. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
  24. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  25. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  26. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  27. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  28. 2022Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairscited by 130
  29. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  30. 2023Non-Parametric Outlier Synthesiscited by 129
  31. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  32. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  33. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  34. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  35. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
  36. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  37. 2023GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detectioncited by 36
  38. 2023Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detectioncited by 19

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  2. 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Modelscited by 21
  3. 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
  4. 2026Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Modelscited by 2
  5. 2025Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detectioncited by 0