mlsanityData to 14 Oct 2026

Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining

arXiv 2601.20333 ↗First posted 28 Jan 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep topological data analysis (TDA) offers a principled framework for capturing structural invariants such as connectivity and cycles that persist across scales, making it a natural fit for anomaly segmentation (AS). Unlike thresholdbased binarisation, which produces brittle masks under distribution shift, TDA allows anomalies to be characterised as disruptions to global structure rather than local fluctuations. We introduce TopoOT, a topology-aware optimal transport (OT) framework that integrates multi-filtration persistence diagrams (PDs) with test-time adaptation (TTA). Our key innovation is Optimal Transport Chaining, which sequentially aligns PDs across thresholds and filtrations, yielding geodesic stability scores that identify features consistently preserved across scales. These stabilityaware pseudo-labels supervise a lightweight head trained online with OT-consistency and contrastive objectives, ensuring robust adaptation under domain shift. Across standard 2D and 3D anomaly detection benchmarks, TopoOT achieves state-of-the-art performance, outperforming the most competitive methods by up to +24.1% mean F1 on 2D datasets and +10.2% on 3D AS benchmarks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 82 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

52 of 82 references.

References · 52

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  4. 2020Point Transformercited by 1,470
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  6. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  8. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  9. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  10. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  11. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
  12. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
38 more
  1. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  2. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  3. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  4. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  5. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  6. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  7. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  8. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  9. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  10. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  11. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  12. 2014A Stable Multi-Scale Kernel for Topological Machine Learningcited by 75
  13. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  14. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  15. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  16. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 68
  17. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  18. 2021SITA: Single Image Test-time Adaptationcited by 59
  19. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  20. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  21. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 42
  22. 2023Topological Deep Learning: A Review of an Emerging Paradigmcited by 34
  23. 2024PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detectioncited by 30
  24. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28
  25. 2022Ev-TTA: Test-Time Adaptation for Event-Based Object Recognitioncited by 26
  26. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  27. 2022On the Road to Online Adaptation for Semantic Image Segmentationcited by 23
  28. 2024AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusioncited by 21
  29. 2018Functional Summaries of Persistence Diagramscited by 19
  30. 2024Supervised Anomaly Detection for Complex Industrial Imagescited by 18
  31. 2023Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restorationcited by 15
  32. 2023To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentationcited by 14
  33. 2024Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentationcited by 12
  34. 2024AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localizationcited by 12
  35. 2024Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localizationcited by 5
  36. 2025Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shiftcited by 5
  37. 2025Progressive Test Time Energy Adaptation for Medical Image Segmentationcited by 5
  38. 2023Neural Network Training Strategy to Enhance Anomaly Detection Performance: A Perspective on Reconstruction Loss Amplificationcited by 4

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.