mlsanityData to 7 Oct 2026

TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection

arXiv 2602.03594 ↗First posted 3 Feb 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Anomaly detection identifies departures from expected behavior in safety-critical settings. When target-domain normal data are unavailable, zero-shot anomaly detection (ZSAD) leverages vision-language models (VLMs). However, CLIP's coarse image-text alignment limits both localization and detection due to (i) spatial misalignment and (ii) weak sensitivity to fine-grained anomalies; prior works compensate with complex auxiliary modules yet largely overlook the choice of backbone. We revisit the backbone and use TIPS-a VLM trained with spatially aware objectives. While TIPS alleviates CLIP's issues, it exposes a distributional gap between global and local features. We address this with decoupled prompts-fixed for image-level detection and learnable for pixel-level localization-and by injecting local evidence into the global score. Without CLIP-specific tricks, our TIPS-based pipeline improves image-level performance by 1.1-3.9% and pixel-level by 1.5-6.9% across seven industrial datasets, delivering strong generalization with a lean architecture. Code is available at github.com/AlirezaSalehy/Tipsomaly.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 35 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

19 of 35 references.

References · 19

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  3. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  4. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  5. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  6. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  7. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  8. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  9. 2016Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)cited by 197
  10. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  11. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  12. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
7 more
  1. 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 128
  2. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 126
  3. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 110
  4. 2023A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingcited by 95
  5. 2016Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenescited by 50
  6. 2024TIPS: Text-Image Pretraining with Spatial awarenesscited by 37
  7. 2025Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detectioncited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer
  2. 2025PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures
  3. 2024Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection
  4. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection
  5. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  6. 2024GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection
  7. 2024FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
  8. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection