MLF-SC: Incorporating multi-layer features to sparse coding for anomaly detection
This work addresses a practical issue in anomaly detection for real-world image data, offering an incremental improvement over existing sparse-coding-based methods.
The authors tackled the problem of anomaly detection in images by proposing MLF-SC, which incorporates multi-scale features into sparse coding to handle anomalies of varying sizes, and demonstrated that it outperforms state-of-the-art methods on the MVTec AD dataset.
Anomalies in images occur in various scales from a small hole on a carpet to a large stain. However, anomaly detection based on sparse coding, one of the widely used anomaly detection methods, has an issue in dealing with anomalies that are out of the patch size employed to sparsely represent images. A large anomaly can be considered normal if seen in a small scale, but it is not easy to determine a single scale (patch size) that works well for all images. Then, we propose to incorporate multi-scale features to sparse coding and improve the performance of anomaly detection. The proposed method, multi-layer feature sparse coding (MLF-SC), employs a neural network for feature extraction, and feature maps from intermediate layers of the network are given to sparse coding, whereas the standard sparse-coding-based anomaly detection method directly works on given images. We show that MLF-SC outperforms state-of-the-art anomaly detection methods including those employing deep learning. Our target data are the texture categories of the MVTec Anomaly Detection (MVTec AD) dataset, which is a modern benchmark dataset consisting of images from the real world. Our idea can be a simple and practical option to deal with practical data.