Learning invariant representation for unsupervised domain adaptive thorax disease classification

Abstract

• It designs a novel UDA framework that learns invariant features for optimizing thorax disease classification . • We propose a novel feature learning scheme that regularizes features concurrently via three types of invariance constraints. • We develop an end-to-end trainable deep network that significantly improves the thorax disease classification performance. Unsupervised Domain Adaptation (UDA) based thorax disease classification is a challenging task due to the data distribution discrepancy between source and target domains, and the lack of labeling information in target domain. In this paper, we present an innovative UDA framework that learns invariant and discriminative feature representations from Chest X-rays (CXR) images for UDA-based thorax disease classification across domains. Specifically, a Convolutional Neural Network (CNN) is adopted that explicitly learns discriminative feature representation from CXR images under the supervision of a labeled source domain. A domain-invariance constraint is designed to further align feature distributions between the labeled source domain and the unlabeled target domain. In addition, an instance-invariance constraint and a perturbation-invariance constraint are designed that guide the learning to capture robust and discriminative features from target CXR images. The proposed method has been evaluated on the ChestX-ray14 and SYSU datasets and the experimental results demonstrate its superior robustness and effectiveness relative to state-of-the-art approaches.