Cross-domain person re-identification using Dual Generation Learning in camera sensor networks

Abstract

Cross-domain person re-identification (Re-ID) in camera sensor networks is a challenge task due to large domain-style and camera-style variances. In this work, we propose a novel deep learning method called Dual Generation Learning (DGL) for cross-domain person Re-ID, which simultaneously considers domain and camera styles by expanding training samples. Correspondingly, we design a three-branch deep model with different losses. We further propose Hybrid Triplet Loss (HTL) to deal with the combination of the source dataset, the target dataset and their expansions. Thus, the learned features are robust to domain shifts and camera differences. The experimental results prove that DGL achieves the promising generalization ability and accuracy compared with the state-of-the-art methods.