mlsanityData to 7 Oct 2026

Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision

arXiv 2606.09670 ↗First posted 8 Jun 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent Anomaly Detection methods achieve perfect detection and segmentation scores on well-established datasets, such as MVTec. However, many of these methods face challenges when foundational assumptions - such as consistent object scale, viewpoint, background, illumination, and centered placement - are violated. Those variations that occur render anomaly detection methods unusable in many real-world scenarios. To address these limitations, we introduce three key contributions: (1) a visual prompting pipeline that isolates objects using foreground-background masking; (2) a mechanism for unfreezing the teacher in student-teacher models to improve domain adaptability; and (3) a data augmentation strategy leveraging diffusion-generated synthetic images to enhance anomaly detection performance. We achieve a 3.5 percentage point improvement over the previous state-of-the-art on the challenging AeBAD dataset by using the Masked Multiscale Reconstruction (MMR) model as our backbone.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

26 of 36 references.

References · 26

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  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. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
  10. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 153
  11. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  12. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
14 more
  1. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  2. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  3. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  4. 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
  5. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  6. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  7. 2023ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detectioncited by 30
  8. 2023Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstructioncited by 22
  9. 2022FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detectioncited by 16
  10. 2022U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Thresholdcited by 16
  11. 2023Zero-Shot Anomaly Detection with Pre-trained Segmentation Modelscited by 8
  12. 2023Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformerscited by 6
  13. 2022FRE: A Fast Method For Anomaly Detection And Segmentationcited by 5
  14. 2024MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detectioncited by 2

Built on by

Not cited yet.