mlsanityData to 14 Oct 2026

TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank

arXiv 2508.21795 ↗First posted 29 Aug 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Anomaly detection, which aims to identify anomalies deviating from normal patterns, is challenging due to the limited amount of normal data available. Unlike most existing unified methods that rely on carefully designed image feature extractors and memory banks to capture logical relationships between objects, we introduce a text memory bank to enhance the detection of logical anomalies. Specifically, we propose a Three-Memory framework for Unified structural and logical Anomaly Detection (TMUAD). First, we build a class-level text memory bank for logical anomaly detection by the proposed logic-aware text extractor, which can capture rich logical descriptions of objects from input images. Second, we construct an object-level image memory bank that preserves complete object contours by extracting features from segmented objects. Third, we employ visual encoders to extract patch-level image features for constructing a patch-level memory bank for structural anomaly detection. These three complementary memory banks are used to retrieve and compare normal images that are most similar to the query image, compute anomaly scores at multiple levels, and fuse them into a final anomaly score. By unifying structural and logical anomaly detection through collaborative memory banks, TMUAD achieves state-of-the-art performance across seven publicly available datasets involving industrial and medical domains. The model and code are available at https://github.com/SIA-IDE/TMUAD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 71 references that are in the map. First posted on arXiv 29 Aug 2025.

Builds on

52 of 71 references.

References · 52

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023Segment Anythingcited by 8,234
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  8. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  9. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  10. 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 518
  11. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  12. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 445
38 more
  1. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  2. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  3. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  4. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  5. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  6. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  7. 2022CREPE: Can Vision-Language Foundation Models Reason Compositionally?cited by 181
  8. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  9. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Modelscited by 164
  10. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  11. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 130
  12. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  13. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  14. 2023From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Modelscited by 98
  15. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  16. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  17. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  18. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  19. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  20. 2023Residual Denoising Diffusion Modelscited by 69
  21. 2024Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Imagescited by 69
  22. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  23. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  24. 2023Detecting Human-Object Contact in Imagescited by 41
  25. 2023ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detectioncited by 30
  26. 2024GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Featurescited by 29
  27. 2024UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detectioncited by 28
  28. 2025Towards Training-free Anomaly Detection with Vision and Language Foundation Modelscited by 26
  29. 2024Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspectivecited by 23
  30. 2025InteractVLM: 3D Interaction Reasoning from 2D Foundational Modelscited by 21
  31. 2022Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimationcited by 20
  32. 2023Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detectioncited by 19
  33. 2023Contextual Affinity Distillation for Image Anomaly Detectioncited by 18
  34. 2024Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detectioncited by 17
  35. 2024SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detectioncited by 14
  36. 2025Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detectioncited by 11
  37. 2024Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detectioncited by 10
  38. 2025LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questionscited by 9

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.