Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation

2025/04/18 by Park, SoYoung, Lee, Hyewon, Choi, Mingyu +4
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2504.13560

Abstract

Anomaly segmentation is essential for industrial quality, maintenance, and stability. Existing text-guided zero-shot anomaly segmentation models are effective but rely on fixed prompts, limiting adaptability in diverse industrial scenarios. This highlights the need for flexible, context-aware prompting strategies. We propose Image-Aware Prompt Anomaly Segmentation (IAP-AS), which enhances anomaly segmentation by generating dynamic, context-aware prompts using an image tagging model and a large language model (LLM). IAP-AS extracts object attributes from images to generate context-aware prompts, improving adaptability and generalization in dynamic and unstructured industrial environments. In our experiments, IAP-AS improves the F1-max metric by up to 10%, demonstrating superior adaptability and generalization. It provides a scalable solution for anomaly segmentation across industries

Citations

• EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
• Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation
• ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
• CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
• Recognize Anything: A Strong Image Tagging Model
• Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models
• Micrograph segmentations for DDEVD
• Segment Anything
• WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
• Fairness-guided Few-shot Prompting for Large Language Models
• Annotated Point Clouds and Images from a Spatial-Semantic Perception Pipeline: Robotized Deconstruction at the Reference Construction Site, Aachen
• LLaMA: Open and Efficient Foundation Language Models
• Anomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors
• MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection
• Image Segmentation Using Text and Image Prompts
• VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization
• Learning Transferable Visual Models From Natural Language Supervision
• Segmentation-Based Deep-Learning Approach for Surface-Defect Detection

Related

• VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation
• FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
• CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection
• Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts
• Automatic Prompt Generation and Grounding Object Detection for Zero-Shot Image Anomaly Detection