mlsanityData to 14 Oct 2026

Language-Assisted Feature Transformation for Anomaly Detection

arXiv 2503.01184 ↗First posted 3 Mar 2025cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces LAFT, a novel feature transformation method designed to incorporate user knowledge and preferences into anomaly detection using natural language. Accurately modeling the boundary of normality is crucial for distinguishing abnormal data, but this is often challenging due to limited data or the presence of nuisance attributes. While unsupervised methods that rely solely on data without user guidance are common, they may fail to detect anomalies of specific interest. To address this limitation, we propose Language-Assisted Feature Transformation (LAFT), which leverages the shared image-text embedding space of vision-language models to transform visual features according to user-defined requirements. Combined with anomaly detection methods, LAFT effectively aligns visual features with user preferences, allowing anomalies of interest to be detected. Extensive experiments on both toy and real-world datasets validate the effectiveness of our method.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 53 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

44 of 53 references.

References · 44

  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. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  7. 2022A ConvNet for the 2020scited by 3,579
  8. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  10. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  11. 2019Invariant Risk Minimizationcited by 1,854
  12. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
32 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  2. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,274
  3. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  4. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 798
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  6. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  7. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  8. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  9. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  11. 2023EVA-02: A Visual Representation for Neon Genesiscited by 381
  12. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  13. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  14. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  15. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  16. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  17. 2023Unleashing Text-to-Image Diffusion Models for Visual Perceptioncited by 269
  18. 2023Data Filtering Networkscited by 250
  19. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  20. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  21. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  22. 2023Hyperbolic Image-Text Representationscited by 136
  23. 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
  24. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  25. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  26. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  27. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  28. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  29. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  30. 2023Anomaly Detection under Distribution Shiftcited by 35
  31. 2023ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detectioncited by 30
  32. 2023No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detectioncited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection
  2. 2024VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection
  3. 2024Vision-Language Models Assisted Unsupervised Video Anomaly Detection
  4. 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
  5. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
  6. 2026Analyzing VLM-Based Approaches for Anomaly Classification and Segmentation
  7. 2026Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
  8. 2025From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge