mlsanityData to 7 Oct 2026

TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection

arXiv 2605.10756 ↗First posted 11 May 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (arXiv)

Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods mainly rely on static negative labels constructed before inference, limiting their ability to cover diverse and evolving OOD concepts. Although test-time expansion provides a natural solution, naively learning negative semantics from potential OOD samples may introduce hard ID contamination. To address this issue, we propose a Test-time ID-prototype-separated Negative Semantics learning method, termed TINS. TINS learns sample-specific negative text embeddings via image-to-text modality inversion and introduces ID-prototype-separated regularization to keep them separated from ID semantics. To further stabilize negative semantics expansion, TINS employs group-wise aggregation scoring and a buffer update strategy. Extensive experiments across Four-OOD, OpenOOD, Temporal-shift, and Various ID settings show consistent improvements over strong baselines. Notably, on the Four-OOD benchmark with ImageNet-1K as ID, TINS reduces the average FPR95 from 14.04% to 6.72%. Our code is available at https://github.com/zxk1212/tins.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 45 of its 62 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

45 of 62 references.

Closest ancestors · 5

Same direction, newest first

  1. 2026Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models26 Mar
  2. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models26 Oct
  3. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models11 Oct
  4. 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models12 Jul
  5. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Models29 Mar

Other references · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2013Describing Textures in the Wildcited by 2,110
  7. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  8. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  12. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
28 more
  1. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  2. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  3. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  4. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  5. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  6. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  7. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  8. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  9. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  10. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  11. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  12. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  13. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  14. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  15. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  16. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  17. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  18. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  19. 2020BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patientscited by 81
  20. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  21. 2023ID-like Prompt Learning for Few-Shot Out-of-Distribution Detectioncited by 42
  22. 2025Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversioncited by 42
  23. 2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detectioncited by 30
  24. 2024AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentationcited by 18
  25. 2025OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionarycited by 16
  26. 2024CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoringcited by 13
  27. 2025ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoningcited by 10
  28. 2026Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection
  2. 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models
  3. 2026Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
  4. 2026Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models
  5. 2025Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models
  6. 2024CMOOD: Concept-based Multi-label OOD Detection
  7. 2025Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection
  8. 2026Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set