mlsanityData to 14 Oct 2026

Text-Guided Multimodal Unified Industrial Anomaly Detection

arXiv 2604.22899 ↗First posted 24 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal alignment caused by the lack of high-level semantic guidance and insufficient geometric modeling for RGB-to-3D feature mapping. To address these issues, we propose a unified multimodal industrial anomaly detection framework guided by text semantics. The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper to preserve geometric structure during modality conversion, and an Object-Conditioned Textual Feature Adaptor to align multimodal features with semantic priors. Furthermore, we establish a unified learning paradigm for multimodal industrial anomaly detection, which breaks the one-model-one-class constraint and enables accurate anomaly detection across diverse classes using a single model. Extensive experiments on the MVTec 3D-AD and Eyecandies datasets demonstrate that our method achieves state-of-the-art performance in classification and localization under unsupervised settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 43 references that are in the map. First posted on arXiv 24 Apr 2026.

Builds on

34 of 43 references.

References · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  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. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  10. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  11. 2022A Unified Model for Multi-class Anomaly Detectioncited by 268
  12. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
22 more
  1. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  2. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  3. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  4. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  5. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  6. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  7. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  8. 2020Deep Nearest Neighbor Anomaly Detectioncited by 104
  9. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  10. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  11. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  12. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  13. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  14. 2022The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localizationcited by 57
  15. 2023EasyNet: An Easy Network for 3D Industrial Anomaly Detectioncited by 43
  16. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 42
  17. 2024Self-supervised Feature Adaptation for 3D Industrial Anomaly Detectioncited by 16
  18. 2025G2SF-MIAD: Geometry-Guided Score Fusion for Multimodal Industrial Anomaly Detectioncited by 7
  19. 2025Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detectioncited by 4
  20. 2025GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detectioncited by 3
  21. 2025BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detectioncited by 2
  22. 2025IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detectioncited by 2

Built on by

Not cited yet.