mlsanityData to 7 Oct 2026

LogiCo: A Unified Framework for Logical and Structural Anomaly Detection

arXiv 2606.28688 ↗First posted 27 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Current anomaly detection methods primarily focus on structural anomalies, while paying insufficient attention to anomalies that violate logical constraints. Conversely, top-performing logical anomaly detection approaches address this by modeling global semantic consistency, but perform poorly on subtle structural anomalies due to inadequate detection granularity. In this paper, we propose LogiCo, a unified framework for Logical and structural anomaly detection via Component-level feature reconstruction. Unlike existing methods that rely on explicit global semantic modeling, LogiCo employs a novel component-level feature reconstruction technique to capture inter-component logical constraints. Specifically, LogiCo maps pre-trained image features into a discrete component-level feature space and performs collaborative feature reconstruction at both component and patch levels, enabling it to effectively detect both logical and structural anomalies. Furthermore, to address the specific challenge of count-related logical anomalies, we integrate a segmentation-map discriminator that extends the model's capability to identify quantitative inconsistencies. LogiCo achieves state-of-the-art performance on both logical and structural anomaly detection across four benchmarks, including MVTec-LOCO, MVTec-AD, VisA, and Real-IAD, demonstrating its superiority and practical feasibility. The code is available at https://github.com/cnulab/LogiCo.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 27 Jun 2026.

Builds on

43 of 54 references.

References · 43

  1. 2023Segment Anythingcited by 8,158
  2. 2025DINOv3cited by 1,297
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  4. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  5. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  6. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  7. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  8. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  9. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  10. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  11. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  12. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
31 more
  1. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  2. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  3. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  4. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  5. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  6. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  7. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 110
  8. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  9. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 89
  10. 2023PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flowcited by 74
  11. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  12. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  13. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  14. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 47
  15. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  16. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  17. 2021SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detectioncited by 34
  18. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Modelscited by 24
  19. 2023Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detectioncited by 21
  20. 2023Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detectioncited by 19
  21. 2022Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Rayscited by 17
  22. 2024Continuous Memory Representation for Anomaly Detectioncited by 16
  23. 2024SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detectioncited by 14
  24. 2024CSAD: Unsupervised Component Segmentation for Logical Anomaly Detectioncited by 11
  25. 2025AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detectioncited by 8
  26. 2024PUAD: Frustratingly Simple Method for Robust Anomaly Detectioncited by 7
  27. 2024LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localizationcited by 6
  28. 2025Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shiftcited by 5
  29. 2025Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detectioncited by 4
  30. 2025Towards High-Resolution Industrial Image Anomaly Detectioncited by 3
  31. 2025SALAD -- Semantics-Aware Logical Anomaly Detectioncited by 3

Built on by

Not cited yet.