A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
This addresses the problem of person re-identification for surveillance and security applications, representing an incremental improvement over existing deep learning approaches.
The paper tackles the poor generalization capability of triplet-based person re-identification systems by proposing a four-stream Siamese CNN that jointly optimizes verification and identification losses over groups of four images. The method achieves state-of-the-art performance on four challenging datasets (VIPeR, CUHK01, CUHK03, PRID2011).
State-of-the-art person re-identification systems that employ a triplet based deep network suffer from a poor generalization capability. In this paper, we propose a four stream Siamese deep convolutional neural network for person redetection that jointly optimises verification and identification losses over a four image input group. Specifically, the proposed method overcomes the weakness of the typical triplet formulation by using groups of four images featuring two matched (i.e. the same identity) and two mismatched images. This allows us to jointly increase the interclass variations and reduce the intra-class variations in the learned feature space. The proposed approach also optimises over both the identification and verification losses, further minimising intra-class variation and maximising inter-class variation, improving overall performance. Extensive experiments on four challenging datasets, VIPeR, CUHK01, CUHK03 and PRID2011, demonstrates that the proposed approach achieves state-of-the-art performance.