Deep Feature Inpainting for Unsupervised Visual Anomaly Detection
Procedia Computer Science(2023)
摘要
Visual anomaly detection is an important and challenging problem in the field of machine learning and computer vision. In this paper, we address the problem of unsupervised visual anomaly detection from the perspective of image feature restoration. We propose deep feature inpainting (DFI) where we develop a deep learning model that can automatically inpainting the normal image patterns or features from the anomalous images by eliminating the irregular structures or patterns. By comparing the anomalous features and their reconstructed counterparts, we can identify and analyze the anomalous structures in the images. Extensive experiments have been carried out to demonstrate the effectiveness of the approach.
更多查看译文
关键词
Visual anomaly detection,feature inpainting,deep learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要