提出统一异常分割框架，提升图像异常定位精度。
Towards Accurate Unified Anomaly Segmentation
- 设计多粒度门控CNN融合Transformer，逐级增强正常特征表示。
- 在MVTec-AD和VisA数据集上分别达65.12/59.33和40.06/32.50的pAP/DSC。
- 采用pAP和DSC评估，更适配不平衡异常分割场景，适合工业质检应用。
无监督异常检测旨在建模正常数据分布，生成判别性表征以区分并精确定位异常。尽管近期已实现高效统一的端到端方案，但在精确分割异常像素方面仍存在挑战，且该问题常被不平衡设置下广泛使用的AUROC指标掩盖。为此，本文强调使用pAP和DSC作为关键评估指标的重要性。为解决未解的分割任务，我们提出统一异常分割框架UniAS，采用多层次混合流水线，从粗到细逐步增强正常信息，并在Transformer层中引入新型多粒度门控卷积网络（MGG-CNN），显式聚合不同粒度的局部细节。UniAS在MVTec-AD和VisA数据集上分别取得65.12/59.33和40.06/32.50的pAP/DSC，显著超越现有方法。代码已开源于https://github.com/Mwxinnn/UniAS。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。