一种结合全局和局部信息的遮蔽反知识蒸馏方法用于图像异常检测
A Masked Reverse Knowledge Distillation Method Incorporating Global and Local Information for Image Anomaly Detection
AI总结：
本文提出一种结合全局和局部信息的遮蔽反知识蒸馏方法，用于提升图像异常检测的性能和泛化能力。
摘要：
知识蒸馏是一种有效的图像异常检测和定位方案。然而，这种方案的主要缺点是其倾向于过度泛化，主要由于输入信号和监督信号之间的相似性。为了解决这个问题，本文介绍了一种新的技术，称为遮蔽反知识蒸馏（MRKD）。通过使用图像级遮蔽（ILM）和特征级遮蔽（FLM），MRKD将图像重建任务转化为图像恢复任务。具体而言，ILM通过区分输入信号和监督信号来捕捉全局信息。另一方面，FLM引入合成的特征级异常，以确保学习到的表示包含足够的局部信息。通过这两种策略，MRKD具备更强的图像上下文捕捉能力，并且更不容易过度泛化。在广泛使用的MVTec异常检测数据集上的实验表明，MRKD实现了令人印象深刻的表现：图像级98.9% AU-ROC，像素级98.4% AU-ROC，以及95.3% AU-PRO。此外，广泛的消融实验已验证了MRKD在缓解过度泛化问题方面的优越性。
英文摘要：
Knowledge distillation is an effective image anomaly detection and localization scheme. However, a major drawback of this scheme is its tendency to overly generalize, primarily due to the similarities between input and supervisory signals. In order to address this issue, this paper introduces a novel technique called masked reverse knowledge distillation (MRKD). By employing image-level masking (ILM) and feature-level masking (FLM), MRKD transforms the task of image reconstruction into image restoration. Specifically, ILM helps to capture global information by differentiating input signals from supervisory signals. On the other hand, FLM incorporates synthetic feature-level anomalies to ensure that the learned representations contain sufficient local information. With these two strategies, MRKD is endowed with stronger image context capture capacity and is less likely to be overgeneralized. Experiments on the widely-used MVTec anomaly detection dataset demonstrate that MRKD achieves impressive performance: image-level 98.9% AU-ROC, pixel-level 98.4% AU-ROC, and 95.3% AU-PRO. In addition, extensive ablation experiments have validated the superiority of MRKD in mitigating the overgeneralization problem.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
