mlsanityData to 14 Oct 2026

MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning

arXiv 2504.06740 ↗First posted 9 Apr 2025cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or not, it is crucial to know the distinct type of defect, such as a bent, cut, or scratch. The ability to recognize the "exact" defect type enables automated treatments of the anomalies in modern production lines. Current methods are limited to solely detecting whether a product is defective or not without providing any insights on the defect type, nevertheless detecting and identifying multiple defects. We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection and Segmentation. The architecture of MultiADS comprises CLIP and extra linear layers to align the visual- and textual representation in a joint feature space. To the best of our knowledge, our proposal, is the first approach to perform a multi-type anomaly segmentation task in zero-shot learning. Contrary to the other baselines, our approach i) generates specific anomaly masks for each distinct defect type, ii) learns to distinguish defect types, and iii) simultaneously identifies multiple defect types present in an anomalous product. Additionally, our approach outperforms zero/few-shot learning SoTA methods on image-level and pixel-level anomaly detection and segmentation tasks on five commonly used datasets: MVTec-AD, Visa, MPDD, MAD and Real-IAD.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 28 of its 47 references that are in the map. First posted on arXiv 9 Apr 2025.

Builds on

28 of 47 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  6. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  7. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  8. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  9. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  10. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  11. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  12. 2019Dice Loss for Data-imbalanced NLP Taskscited by 182
16 more
  1. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  2. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  3. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  4. 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
  5. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  6. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  7. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  8. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  9. 2023Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcorecited by 75
  10. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  11. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  12. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  13. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  14. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  15. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  16. 2024Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detectioncited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 5.

12 papers.

  1. 2025Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guaranteescited by 9
  2. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparisoncited by 5
  3. 2026GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learningcited by 4
  4. 2025GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detectioncited by 3
  5. 2025Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learningcited by 0
  6. 2025UniADC: A Unified Framework for Anomaly Detection and Classificationcited by 0
  7. 2025Explainable Deep Convolutional Multi-Type Anomaly Detectioncited by 0
  8. 2025ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarioscited by 0
  9. 2025Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentationcited by 0
  10. 2026GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Modelscited by 0
  11. 2026Understanding and Overcoming Cross-modal Fusion Bias in Multimodal Anomaly Detection From A Fisher Information Perspectivecited by 0
  12. 2026PADFormer: Pose-agnostic Anomaly Detection from Sparse View Imagescited by 0