mlsanityData to 7 Oct 2026

Semantic-Deviation-Anchored Multi-Branch Fusion for Unsupervised Anomaly Detection and Localization in Unstructured Conveyor-Belt Coal Scenes

arXiv 2602.07694 ↗First posted 7 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Reliable foreign-object anomaly detection and pixel-level localization in conveyor-belt coal scenes are essential for safe and intelligent mining operations. This task is particularly challenging due to the highly unstructured environment: coal and gangue are randomly piled, backgrounds are complex and variable, and foreign objects often exhibit low contrast, deformation, occlusion, resulting in coupling with their surroundings. These characteristics weaken the stability and regularity assumptions that many anomaly detection methods rely on in structured industrial settings, leading to notable performance degradation. To support evaluation and comparison in this setting, we construct CoalAD, a benchmark for unsupervised foreign-object anomaly detection with pixel-level localization in coal-stream scenes. We further propose a complementary-cue collaborative perception framework that extracts and fuses complementary anomaly evidence from three perspectives: object-level semantic composition modeling, semantic-attribution-based global deviation analysis, and fine-grained texture matching. The fused outputs provide robust image-level anomaly scoring and accurate pixel-level localization. Experiments on CoalAD demonstrate that our method outperforms widely used baselines across the evaluated image-level and pixel-level metrics, and ablation studies validate the contribution of each component. The code is available at https://github.com/xjpp2016/USAD.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 7 Feb 2026.

Builds on

32 of 44 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  6. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  7. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  8. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  9. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  10. 2016Tutorial on Variational Autoencoderscited by 404
  11. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  12. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
20 more
  1. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  2. 2023RoMa: Robust Dense Feature Matchingcited by 296
  3. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  4. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  5. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  6. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  7. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  8. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  9. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  10. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  11. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detectioncited by 46
  12. 2021Learning Not to Reconstruct Anomaliescited by 31
  13. 2018Anomaly Detection using Deep Learning based Image Completioncited by 27
  14. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  15. 2023Component-aware anomaly detection framework for adjustable and logical industrial visual inspectioncited by 22
  16. 2024PUAD: Frustratingly Simple Method for Robust Anomaly Detectioncited by 7
  17. 2024Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learningcited by 7
  18. 2025Aligning First, Then Fusing: A Novel Weakly Supervised Multimodal Violence Detection Methodcited by 5
  19. 2023ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localizationcited by 4
  20. 2025Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Eracited by 2

Built on by

Not cited yet.