English

Segment Any Anomaly without Training via Hybrid Prompt Regularization

Computer Vision and Pattern Recognition 2025-02-17 v1 Artificial Intelligence

Abstract

We present a novel framework, i.e., Segment Any Anomaly + (SAA+), for zero-shot anomaly segmentation with hybrid prompt regularization to improve the adaptability of modern foundation models. Existing anomaly segmentation models typically rely on domain-specific fine-tuning, limiting their generalization across countless anomaly patterns. In this work, inspired by the great zero-shot generalization ability of foundation models like Segment Anything, we first explore their assembly to leverage diverse multi-modal prior knowledge for anomaly localization. For non-parameter foundation model adaptation to anomaly segmentation, we further introduce hybrid prompts derived from domain expert knowledge and target image context as regularization. Our proposed SAA+ model achieves state-of-the-art performance on several anomaly segmentation benchmarks, including VisA, MVTec-AD, MTD, and KSDD2, in the zero-shot setting. We will release the code at \href{https://github.com/caoyunkang/Segment-Any-Anomaly}{https://github.com/caoyunkang/Segment-Any-Anomaly}.

Keywords

Cite

@article{arxiv.2305.10724,
  title  = {Segment Any Anomaly without Training via Hybrid Prompt Regularization},
  author = {Yunkang Cao and Xiaohao Xu and Chen Sun and Yuqi Cheng and Zongwei Du and Liang Gao and Weiming Shen},
  journal= {arXiv preprint arXiv:2305.10724},
  year   = {2025}
}

Comments

The first two authors contribute equally. The code will be available on https://github.com/caoyunkang/Segment-Any-Anomaly

R2 v1 2026-06-28T10:37:51.835Z