mlsanityData to 14 Oct 2026

ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection

arXiv 2607.02252 ↗First posted 2 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The deployment of Industrial Anomaly Detection (IAD) in real-world manufacturing frequently encounters a challenging cold-start bottleneck, in which limited normal samples fail to represent the full normal distribution and only a few anomalies are available. Under such a regime, existing methods struggle to form compact normal boundaries and fail to effectively exploit supervised signals from rare defects. To address this challenge, we propose Anomaly-Rectified Cold-start AD (ArcAD), a plug-and-play calibration framework for reconstruction-based IAD baselines. ArcAD follows a push-pull learning paradigm to construct a compact and discriminative normal boundary under data scarcity. On the one hand, ArcAD projects limited normal samples onto a hypersphere and pulls them into multiple compact clusters to maximize coverage of the normal manifold. On the other hand, it synthesizes pseudo-anomalies on the hypersphere and leverages real anomalies to push the boundary inward and sharpen anomaly discrimination. Extensive experiments on MVTec-AD, VisA, Real-IAD, and MANTA demonstrate that ArcAD significantly outperforms state-of-the-art supervised and unsupervised methods in both single-class and multi-class settings under cold-start conditions. Code is available at: https://github.com/LGC-AD/ArcAD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

42 of 55 references.

References · 42

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  4. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  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. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  8. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  9. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  10. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  11. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  12. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
30 more
  1. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
  2. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  3. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  4. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  5. 2018Hyperspherical Variational Auto-Encoderscited by 189
  6. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  7. 2019Deep Anomaly Detection with Deviation Networkscited by 153
  8. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  9. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  10. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  11. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  12. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  13. 2019SegSort: Segmentation by Discriminative Sorting of Segmentscited by 96
  14. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
  15. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  16. 2024nGPT: Normalized Transformer with Representation Learning on the Hyperspherecited by 70
  17. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  18. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 63
  19. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  20. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  21. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28
  22. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  23. 2023Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detectioncited by 25
  24. 2025Hyperspherical Latents Improve Continuous-Token Autoregressive Generationcited by 16
  25. 2024Salvaging the Overlooked: Leveraging Class-Aware Contrastive Learning for Multi-Class Anomaly Detectioncited by 15
  26. 2025Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detectioncited by 10
  27. 2025Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detectioncited by 6
  28. 2025Dinomaly2: A Unified Framework for Unsupervised Image Anomaly Detectioncited by 6
  29. 2024Learning Multi-Manifold Embedding for Out-Of-Distribution Detectioncited by 3
  30. 2025ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categoriescited by 2

Built on by

Not cited yet.