mlsanityData to 14 Oct 2026

Supervised Anomaly Detection for Complex Industrial Images

arXiv 2405.04953 ↗First posted 8 May 2024cs.CV cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Automating visual inspection in industrial production lines is essential for increasing product quality across various industries. Anomaly detection (AD) methods serve as robust tools for this purpose. However, existing public datasets primarily consist of images without anomalies, limiting the practical application of AD methods in production settings. To address this challenge, we present (1) the Valeo Anomaly Dataset (VAD), a novel real-world industrial dataset comprising 5000 images, including 2000 instances of challenging real defects across more than 20 subclasses. Acknowledging that traditional AD methods struggle with this dataset, we introduce (2) Segmentation-based Anomaly Detector (SegAD). First, SegAD leverages anomaly maps as well as segmentation maps to compute local statistics. Next, SegAD uses these statistics and an optional supervised classifier score as input features for a Boosted Random Forest (BRF) classifier, yielding the final anomaly score. Our SegAD achieves state-of-the-art performance on both VAD (+2.1% AUROC) and the VisA dataset (+0.4% AUROC). The code and the models are publicly available.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

24 of 37 references.

References · 24

  1. 2023Segment Anythingcited by 8,234
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2016Wide Residual Networkscited by 3,070
  4. 2015Variational Inference with Normalizing Flowscited by 2,170
  5. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  6. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  8. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  9. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  10. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  11. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  12. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
12 more
  1. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  2. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  3. 2019Deep Anomaly Detection with Deviation Networkscited by 153
  4. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  5. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  6. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  7. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  8. 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
  9. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  10. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  11. 2022Prototypical Residual Networks for Anomaly Detection and Localizationcited by 56
  12. 2020Deep Learning Models for Visual Inspection on Automotive Assembling Linecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 7.

18 papers.

Sort:

By area:

  1. 2025Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detectioncited by 10
  2. 2025Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learningcited by 8
  3. 2026MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptationcited by 6
  4. 2025No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimescited by 4
  5. 2025ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defectscited by 2
  6. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  7. 2025STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignmentcited by 2
  8. 2025WDT-MD: Wavelet Diffusion Transformers for Microaneurysm Detection in Fundus Imagescited by 2
  9. 2025Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detectioncited by 1
  10. 2025Few-shot Human Action Anomaly Detection via a Unified Contrastive Learning Frameworkcited by 1
  11. 2026SPG: Sparse-Projected Guides with Sparse Autoencoders for Zero-Shot Anomaly Detectioncited by 1
  12. 2024Anomaly Detection from a Tensor Train Perspectivecited by 0
6 more
  1. 2024BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detectioncited by 0
  2. 2026Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chainingcited by 0
  3. 2026PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learningcited by 0
  4. 2026CAD 100K: A Comprehensive Multi-Task Dataset for Car Related Visual Anomaly Detectioncited by 0
  5. 2026Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detectioncited by 0
  6. 2026Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentationcited by 0