mlsanityData to 7 Oct 2026

StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection

arXiv 2602.17048 ↗First posted 19 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD). However, because it relies on a single extreme response, it discards most information about how anomaly evidence is distributed and structured across the image, often causing normal and anomalous scores to overlap. We propose StructCore, a training-free, structure-aware image-level scoring method that goes beyond max pooling. Given an anomaly score map, StructCore computes a low-dimensional structural descriptor phi(S) that captures distributional and spatial characteristics, and refines image-level scoring via a diagonal Mahalanobis calibration estimated from train-good samples, without modifying pixel-level localization. StructCore achieves image-level AUROC scores of 99.6% on MVTec AD and 98.4% on VisA, demonstrating robust image-level anomaly detection by exploiting structural signatures missed by max pooling.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 19 Feb 2026.

Builds on

34 of 49 references.

References · 34

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  6. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  9. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  10. 2015Towards Open Set Deep Networkscited by 533
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  12. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
22 more
  1. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  2. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  3. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  4. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  5. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  6. 2015Bilinear CNNs for Fine-grained Visual Recognitioncited by 228
  7. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  8. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  9. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  10. 2020COPOD: Copula-Based Outlier Detectioncited by 143
  11. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  12. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  13. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  14. 2018Global Second-order Pooling Convolutional Networkscited by 66
  15. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 62
  16. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  17. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  18. 2019Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalizationcited by 42
  19. 2018Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutionscited by 22
  20. 2023UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detectioncited by 11
  21. 2025AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detectioncited by 8
  22. 2026GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detectioncited by 2

Built on by

Not cited yet.