MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning

TL;DR

MetaUAS introduces a novel vision-only, one-prompt meta-learning approach for universal anomaly segmentation, eliminating the need for language models and special datasets, and effectively generalizing to unseen anomalies.

Contribution

It presents the first pure vision model for universal anomaly segmentation using one prompt, leveraging synthetic data and a soft feature alignment module for robust generalization.

Findings

Outperforms previous zero-shot, few-shot, and full-shot methods

Effective on unseen real-world anomalies

Does not rely on language guidance or specialized datasets

Abstract

Zero- and few-shot visual anomaly segmentation relies on powerful vision-language models that detect unseen anomalies using manually designed textual prompts. However, visual representations are inherently independent of language. In this paper, we explore the potential of a pure visual foundation model as an alternative to widely used vision-language models for universal visual anomaly segmentation. We present a novel paradigm that unifies anomaly segmentation into change segmentation. This paradigm enables us to leverage large-scale synthetic image pairs, featuring object-level and local region changes, derived from existing image datasets, which are independent of target anomaly datasets. We propose a one-prompt Meta-learning framework for Universal Anomaly Segmentation (MetaUAS) that is trained on this synthetic dataset and then generalizes well to segment any novel or unseen visual anomalies in the real world. To handle geometrical variations between prompt and query images, we propose a soft feature alignment module that bridges paired-image change perception and single-image semantic segmentation. This is the first work to achieve universal anomaly segmentation using a pure vision model without relying on special anomaly detection datasets and pre-trained visual-language models. Our method effectively and efficiently segments any anomalies with only one normal image prompt and enjoys training-free without guidance from language. Our MetaUAS significantly outperforms previous zero-shot, few-shot, and even full-shot anomaly segmentation methods. The code and pre-trained models are available at https://github.com/gaobb/MetaUAS.