mlsanityData to 14 Oct 2026

PSMP-CLIP: Patch-Prompt SAM and Multi-Semantic Prompting for CLIP-Based Zero-Shot Anomaly Detection

arXiv 2609.16785 ↗First posted 15 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Zero-shot anomaly detection aims to localize anomalies without target-domain samples. Existing CLIP-based methods suffer from coarse anomaly maps and limited semantic prompts. We propose PSMP-CLIP, integrating patch-prompt SAM2 segmentation (PPSS) and multi-semantic guided prompt regularization (MSGPR). PPSS samples prompts directly from intermediate patch features, avoiding threshold drift and guiding SAM2 to produce precise masks. MSGPR uses multiple learnable prompts constrained by semantic anchors to preserve generalization. Experiments on 14 datasets show highly competitive performance, achieving the best pixel-level AUROC on MVTec AD, BTAD, DTD-Synthetic, CVC-ClinicDB, TN3K, Endo, and Kvasir.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 15 Sep 2026.

Builds on

14 of 25 references.

References · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  4. 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 589
  5. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  6. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  7. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  8. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  9. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  10. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  11. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  12. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
2 more
  1. 2026MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrievalcited by 6
  2. 2025MSGCoOp: Multiple Semantic-Guided Context Optimization for Few-Shot Learningcited by 1

Built on by

Not cited yet.