mlsanityData to 7 Oct 2026

Referring Industrial Anomaly Segmentation

arXiv 2602.03673 ↗First posted 3 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manual thresholds, while supervised methods overfit due to scarce, imbalanced data. Both suffer from the "One Anomaly Class, One Model" limitation. To address this, we propose Referring Industrial Anomaly Segmentation (RIAS), a paradigm leveraging language to guide detection. RIAS generates precise masks from text descriptions without manual thresholds and uses universal prompts to detect diverse anomalies with a single model. We introduce the MVTec-Ref dataset to support this, designed with diverse referring expressions and focusing on anomaly patterns, notably with 95% small anomalies. We also propose the Dual Query Token with Mask Group Transformer (DQFormer) benchmark, enhanced by Language-Gated Multi-Level Aggregation (LMA) to improve multi-scale segmentation. Unlike traditional methods using redundant queries, DQFormer employs only "Anomaly" and "Background" tokens for efficient visual-textual integration. Experiments demonstrate RIAS's effectiveness in advancing IAD toward open-set capabilities. Code: https://github.com/swagger-coder/RIAS-MVTec-Ref.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

32 of 42 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  8. 2018MAttNet: Modular Attention Network for Referring Expression Comprehensioncited by 427
  9. 2021CRIS: CLIP-Driven Referring Image Segmentationcited by 353
  10. 2021LAVT: Language-Aware Vision Transformer for Referring Image Segmentationcited by 347
  11. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  12. 2016Segmentation from Natural Language Expressionscited by 257
20 more
  1. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  2. 2023GRES: Generalized Referring Expression Segmentationcited by 252
  3. 2021Vision-Language Transformer and Query Generation for Referring Segmentationcited by 239
  4. 2020Classification-Based Anomaly Detection for General Datacited by 210
  5. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  6. 2019Deep Anomaly Detection with Deviation Networkscited by 152
  7. 2022ReSTR: Convolution-free Referring Image Segmentation Using Transformerscited by 112
  8. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  9. 2020Linguistic Structure Guided Context Modeling for Referring Image Segmentationcited by 102
  10. 2018Anomaly Detection using One-Class Neural Networkscited by 82
  11. 2014Toward Supervised Anomaly Detectioncited by 73
  12. 2021Explainable Deep Few-shot Anomaly Detection with Deviation Networkscited by 69
  13. 2023Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentationcited by 61
  14. 2023Contrastive Grouping with Transformer for Referring Image Segmentationcited by 54
  15. 2019Referring Expression Object Segmentation with Caption-Aware Consistencycited by 46
  16. 2023Active Teacher for Semi-Supervised Object Detectioncited by 43
  17. 2023Weakly Supervised Open-Vocabulary Object Detectioncited by 11
  18. 2023Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understandingcited by 10
  19. 2025Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentationcited by 2
  20. 2025What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentationcited by 2

Built on by

Not cited yet.