PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimation

Image anomaly detection is a binary classification problem that decides whether an input image contains an anomaly or not. Image anomaly localization is to further localize the anomalous region at the pixel level. Due to recent advances in deep learning and availability of new datasets, recent research works are no longer limited to the image-level anomaly detection result, but also show a significant interest in the pixel-level localization of anomaly regions. Image anomaly detection and localization find real-world applications such as manufacturing process monitoring[1], medical image analysis [2, 3], and video surveillance analysis [4, 5]. Most well-studied localization solutions (e.g., semantic segmentation) rely on heavy supervision, where a large number of pixel-level labels and many labeled images are needed. However, in the context of image anomaly detection and localization, a typical assumption is that only normal (i.e., artifact-free) images are available in the training stage.