Towards Accurate Unified Anomaly Segmentation

TL;DR

This paper introduces UniAS, a novel multi-level hybrid pipeline with a multi-granularity gated CNN integrated into Transformer layers, significantly improving anomaly segmentation accuracy on benchmark datasets.

Contribution

UniAS is the first unified approach explicitly designed for precise anomaly segmentation, combining multi-level features with a novel gated CNN within Transformer architecture.

Findings

Achieves state-of-the-art pAP and DSC scores on MVTec-AD and VisA datasets.

Outperforms previous methods significantly in anomaly segmentation.

Highlights the importance of precise segmentation metrics over AUROC in imbalanced UAD settings.

Abstract

Unsupervised anomaly detection (UAD) from images strives to model normal data distributions, creating discriminative representations to distinguish and precisely localize anomalies. Despite recent advancements in the efficient and unified one-for-all scheme, challenges persist in accurately segmenting anomalies for further monitoring. Moreover, this problem is obscured by the widely-used AUROC metric under imbalanced UAD settings. This motivates us to emphasize the significance of precise segmentation of anomaly pixels using pAP and DSC as metrics. To address the unsolved segmentation task, we introduce the Unified Anomaly Segmentation (UniAS). UniAS presents a multi-level hybrid pipeline that progressively enhances normal information from coarse to fine, incorporating a novel multi-granularity gated CNN (MGG-CNN) into Transformer layers to explicitly aggregate local details from different granularities. UniAS achieves state-of-the-art anomaly segmentation performance, attaining 65.12/59.33 and 40.06/32.50 in pAP/DSC on the MVTec-AD and VisA datasets, respectively, surpassing previous methods significantly. The codes are shared at https://github.com/Mwxinnn/UniAS.