Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection
cs.CV, cs.AI
Submitted: 2026-10-04
Updated: 2026-10-04
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- UMIT: Unifying Medical Imaging Tasks via Vision-Language Models
- IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning
- VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection
- Dice Loss for Data-imbalanced NLP Tasks
- Sub-Image Anomaly Detection with Deep Pyramid Correspondences
- Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models