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

Abstract

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.

Published in WACV 2018

References in corpus (7)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deep Learning Face Representation by Joint Identification-Verification
• A Discriminatively Learned CNN Embedding for Person Re-identification
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• End-to-End Comparative Attention Networks for Person Re-identification
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks
• Deep Ranking for Person Re-identification via Joint Representation Learning

Cited by in corpus (3)

• Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
• Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization
• Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification