Self-supervised Detransformation Autoencoder for Representation Learning in Open Set Recognition

Jingyun Jia, Philip K. Chan

Abstract: The objective of Open set recognition (OSR) is to learn a classifier that can reject the unknown samples while classifying the known classes accurately. In this paper, we propose a self-supervision method, Detransformation Autoencoder (DTAE), for the OSR problem. This proposed method engages in learning representations that are invariant to the transformations of the input data. Experiments on several standard image datasets indicate that the pre-training process significantly improves the model performance in the OSR tasks. Moreover, our analysis indicates that DTAE can yield representations that contain some class information even without class labels.