Angular Triplet Loss-based Camera Network for ReID
This addresses the challenge of deploying ReID in real-world applications by reducing computational complexity while handling multi-camera domain gaps, though it is incremental as it builds on existing loss and network ideas.
The paper tackles the problem of person re-identification (ReID) by proposing ATCN, a lightweight camera network that uses angular triplet loss to learn discriminative global features, achieving compelling performance that outperforms many state-of-the-art approaches on benchmark datasets.
Person re-identification (ReID) is a challenging crosscamera retrieval task to identify pedestrians. Many complex network structures are proposed recently and many of them concentrate on multi-branch features to achieve high performance. However, they are too heavy-weight to deploy in realworld applications. Additionally, pedestrian images are often captured by different surveillance cameras, so the varied lights, perspectives and resolutions result in inevitable multi-camera domain gaps for ReID. To address these issues, this paper proposes ATCN, a simple but effective angular triplet loss-based camera network, which is able to achieve compelling performance with only global features. In ATCN, a novel angular distance is introduced to learn a more discriminative feature representation in the embedding space. Meanwhile, a lightweight camera network is designed to transfer global features to more discriminative features. ATCN is designed to be simple and flexible so it can be easily deployed in practice. The experiment results on various benchmark datasets show that ATCN outperforms many SOTA approaches.