Collaborative Networks for Person Verification

This paper considers the person verification problem in video surveillance systems. The goal is to verify whether or not a given pair of human body images belong to the same identity. For this purpose, we propose a method of collaborative networks which contains two kinds of novel agents. Specifically, one is implemented by an improved siamese network (iSN) and the other is employed as a deep discriminative network (DDN). The iSN explores the commonness and difference properties of pairwise feature vectors to enhance the robustness for person verification. Instead, the DDN learns to discriminate the difference of input images from the original difference space, without individual feature extraction. Both of the networks capture the correlation of the input and determine whether they are the same or not. Moreover, we introduce a collaborative learning strategy to fuse them into a unified architecture. Extensive experiments are conducted on four person verification datasets, including CUHK01, CUHK03, PRID2011 and QMUL GRID. We obtain competitive or superior performance compared to state-of-the-art methods.