Research Area:  Machine Learning
We present a novel deep-learning-based approach for one-class transfer learning in which labeled data from an unrelated task is used for feature learning in one-class classification. The proposed method operates on top of a convolutional neural network (CNN) of choice and produces descriptive features while maintaining a low intra-class variance in the feature space for the given class. For this purpose two loss functions, compactness loss and descriptiveness loss, are proposed along with a parallel CNN architecture. A template matching-based framework is introduced to facilitate the testing process. Extensive experiments on publicly available anomaly detection, novelty detection, and mobile active authentication datasets show that the proposed deep one-class (DOC) classification method achieves significant improvements over the state-of-the-art.
Author(s) Name:  Pramuditha Perera, Vishal M. Patel
Journal name:  IEEE Transactions on Image Processing
Publisher name:  ACM
Paper Link:   https://dl.acm.org/doi/10.1109/TIP.2019.2917862