A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-Detection

Amena Khatun, Simon Denman, Sridha Sridharan, Clinton Fookes
2018 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)  
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
more » ... (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.
doi:10.1109/wacv.2018.00146 dblp:conf/wacv/KhatunDSF18 fatcat:nqktns6gungdfguehpr4k4osne