Spatially-weighted Anomaly Detection
This work addresses anomaly detection for applications like medical screening and quality checking, but it appears incremental as it builds on existing methods by incorporating known patterns and noise reduction.
The paper tackled the problem of anomaly detection in images where some anomaly patterns are known but dismissed by previous methods, and proposed SPADE, a spatially-weighted method using Grad-CAM to utilize known patterns and reduce noise vulnerability, achieving quantitative evaluation on MNIST with noise and a dementia screening dataset.
Many types of anomaly detection methods have been proposed recently, and applied to a wide variety of fields including medical screening and production quality checking. Some methods have utilized images, and, in some cases, a part of the anomaly images is known beforehand. However, this kind of information is dismissed by previous methods, because the methods can only utilize a normal pattern. Moreover, the previous methods suffer a decrease in accuracy due to negative effects from surrounding noises. In this study, we propose a spatially-weighted anomaly detection method (SPADE) that utilizes all of the known patterns and lessens the vulnerability to ambient noises by applying Grad-CAM, which is the visualization method of a CNN. We evaluated our method quantitatively using two datasets, the MNIST dataset with noise and a dataset based on a brief screening test for dementia.