CVPR2023

SimpleNet: A Simple Network for Image Anomaly Detection and Localization

Zhikang Liu, Yiming Zhou, Yuansheng Xu, Zilei Wang

摘要

Screw Transistor Cable Bottle Metal_nut Hazelnut Pill Wood Carpet Grid Toothbrush Leather Zipper Capsule Tile Figure 1. Visualization of samples in MVTec AD. The produced anomaly maps superimposed on the images. Anomaly region of high anomaly score is colored with orange. The red boundary denotes contours of actual segmentation maps for anomalies.