A discriminatively learned CNN embedding for person reidentification

Publication Type:
Journal Article
Citation:
ACM Transactions on Multimedia Computing, Communications and Applications, 2017, 14 (1)
Issue Date:
2017-12-01
Metrics:
Full metadata record
Files in This Item:
Filename Description Size
1611.05666.pdfPublished Version5.1 MB
Adobe PDF
© 2017 ACM. In this article, we revisit two popular convolutional neural networks in person re-identification (re-ID): verification and identification models. The two models have their respective advantages and limitations due to different loss functions. Here, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a Siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Our method can be easily applied on different pretrained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show that our architecture can also be applied to image retrieval.
Please use this identifier to cite or link to this item: