mlsanityData to 7 Oct 2026

OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary

arXiv 2503.10468 ↗First posted 13 Mar 2025cs.CV cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection remains challenging for deep learning models, particularly when test-time OOD samples differ significantly from training outliers. We propose OODD, a novel test-time OOD detection method that dynamically maintains and updates an OOD dictionary without fine-tuning. Our approach leverages a priority queue-based dictionary that accumulates representative OOD features during testing, combined with an informative inlier sampling strategy for in-distribution (ID) samples. To ensure stable performance during early testing, we propose a dual OOD stabilization mechanism that leverages strategically generated outliers derived from ID data. To our best knowledge, extensive experiments on the OpenOOD benchmark demonstrate that OODD significantly outperforms existing methods, achieving a 26.0% improvement in FPR95 on CIFAR-100 Far OOD detection compared to the state-of-the-art approach. Furthermore, we present an optimized variant of the KNN-based OOD detection framework that achieves a 3x speedup while maintaining detection performance.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

29 of 41 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  5. 2013Describing Textures in the Wildcited by 2,110
  6. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  10. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  11. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  12. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
17 more
  1. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  2. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  3. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  4. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  5. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  6. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  7. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  8. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  9. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  10. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  11. 2023On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigmcited by 107
  12. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  13. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 65
  14. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  15. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 42
  16. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
  17. 2024A Unified Approach Towards Active Learning and Out-of-Distribution Detectioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 15.

16 papers.

Sort:

By area:

  1. 2025ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoningcited by 10
  2. 2026DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectorscited by 3
  3. 2026TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Modelscited by 2
  4. 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysiscited by 1
  5. 2026Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMscited by 1
  6. 2026Tracking the Discriminative Axis: Dual Prototypes for Test-Time OOD Detection Under Covariate Shiftcited by 0
  7. 2026How to Achieve Prototypical Birth and Death for OOD Detection?cited by 0
  8. 2026DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detectioncited by 0
  9. 2026Autonomous Drift Learning in Data Streams: A Unified Perspectivecited by 0
  10. 2026TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detectioncited by 0
  11. 2026An RRAM-based Hardware Implementation of a Radial Basis Function Neuron for Edge Classifierscited by 0
  12. 2026Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibrationcited by 0
4 more
  1. 2026Deep Convolutional Large-Margin ℓp-SVDD for Visual Anomaly Detectioncited by 0
  2. 2026Training-Free Out-of-Distribution Detection for Pathology Whole-Slide Imagescited by 0
  3. 2026CHILD: Human-in-the-Loop OOD Detection for Safe Clinical Deploymentcited by 0
  4. 2026Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptationcited by 0