Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.16157 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908498843926528 |
|---|---|
| author | Chen, Pi-Wei Lin, Jerry Chun-Wei Chen, Wei-Han Ji, Jia Chen, Zih-Ching Yeh, Feng-Hao Chen, Chao-Chun |
| author_facet | Chen, Pi-Wei Lin, Jerry Chun-Wei Chen, Wei-Han Ji, Jia Chen, Zih-Ching Yeh, Feng-Hao Chen, Chao-Chun |
| contents | Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples, leading to significant gaps in context-specific anomaly understanding. In this paper, we propose \textbf{A}daptive \textbf{P}rompt \textbf{T}uning with semantic alignment for anomaly detection (APT), a groundbreaking prior knowledge-free, few-shot framework and overcomes the limitations of traditional prompt-based approaches. APT uses self-generated anomaly samples with noise perturbations to train learnable prompts that capture context-dependent anomalies in different scenarios. To prevent overfitting to synthetic noise, we propose a Self-Optimizing Meta-prompt Guiding Scheme (SMGS) that iteratively aligns the prompts with general anomaly semantics while incorporating diverse synthetic anomaly. Our system not only advances pixel-wise anomaly detection, but also achieves state-of-the-art performance on multiple benchmark datasets without requiring prior knowledge for prompt crafting, establishing a robust and versatile solution for real-world anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16157 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Human-prompting: Adaptive Prompt Tuning with Semantic Alignment for Anomaly Detection Chen, Pi-Wei Lin, Jerry Chun-Wei Chen, Wei-Han Ji, Jia Chen, Zih-Ching Yeh, Feng-Hao Chen, Chao-Chun Computer Vision and Pattern Recognition Artificial Intelligence Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples, leading to significant gaps in context-specific anomaly understanding. In this paper, we propose \textbf{A}daptive \textbf{P}rompt \textbf{T}uning with semantic alignment for anomaly detection (APT), a groundbreaking prior knowledge-free, few-shot framework and overcomes the limitations of traditional prompt-based approaches. APT uses self-generated anomaly samples with noise perturbations to train learnable prompts that capture context-dependent anomalies in different scenarios. To prevent overfitting to synthetic noise, we propose a Self-Optimizing Meta-prompt Guiding Scheme (SMGS) that iteratively aligns the prompts with general anomaly semantics while incorporating diverse synthetic anomaly. Our system not only advances pixel-wise anomaly detection, but also achieves state-of-the-art performance on multiple benchmark datasets without requiring prior knowledge for prompt crafting, establishing a robust and versatile solution for real-world anomaly detection. |
| title | Beyond Human-prompting: Adaptive Prompt Tuning with Semantic Alignment for Anomaly Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.16157 |