Deep Anomaly Detection Using Geometric Transformations
It addresses the problem of identifying anomalous images for applications like security or quality control, representing a strong specific gain in the field.
The paper tackles anomaly detection in images by training a deep neural model to discriminate between geometric transformations, achieving state-of-the-art improvements in detecting out-of-distribution images.
We consider the problem of anomaly detection in images, and present a new detection technique. Given a sample of images, all known to belong to a "normal" class (e.g., dogs), we show how to train a deep neural model that can detect out-of-distribution images (i.e., non-dog objects). The main idea behind our scheme is to train a multi-class model to discriminate between dozens of geometric transformations applied on all the given images. The auxiliary expertise learned by the model generates feature detectors that effectively identify, at test time, anomalous images based on the softmax activation statistics of the model when applied on transformed images. We present extensive experiments using the proposed detector, which indicate that our algorithm improves state-of-the-art methods by a wide margin.