Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt

TL;DR

This paper introduces UCAD, an unsupervised continual anomaly detection framework using contrastively-learned prompts and structure-based contrastive learning with SAM, addressing catastrophic forgetting and improving anomaly segmentation in industrial settings.

Contribution

The paper proposes a novel UCAD framework with a Continual Prompting Module and Structure-based Contrastive Learning, enabling effective unsupervised continual anomaly detection and segmentation.

Findings

Outperforms existing anomaly detection methods in continual learning settings.

Effectively mitigates catastrophic forgetting with contrastively-learned prompts.

Achieves superior anomaly segmentation results using SAM-based structure learning.

Abstract

Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible. However, continual learning methods primarily rely on supervised annotations, while the application in UAD is limited due to the absence of supervision. Current UAD methods train separate models for different classes sequentially, leading to catastrophic forgetting and a heavy computational burden. To address this issue, we introduce a novel Unsupervised Continual Anomaly Detection framework called UCAD, which equips the UAD with continual learning capability through contrastively-learned prompts. In the proposed UCAD, we design a Continual Prompting Module (CPM) by utilizing a concise key-prompt-knowledge memory bank to guide task-invariant `anomaly' model predictions using task-specific `normal' knowledge. Moreover, Structure-based Contrastive Learning (SCL) is designed with the Segment Anything Model (SAM) to improve prompt learning and anomaly segmentation results. Specifically, by treating SAM's masks as structure, we draw features within the same mask closer and push others apart for general feature representations. We conduct comprehensive experiments and set the benchmark on unsupervised continual anomaly detection and segmentation, demonstrating that our method is significantly better than anomaly detection methods, even with rehearsal training. The code will be available at https://github.com/shirowalker/UCAD.