pith. sign in

arxiv: 1908.05860 · v1 · pith:U3PDVPYCnew · submitted 2019-08-16 · 💻 cs.CV

Learning Deep Representations by Mutual Information for Person Re-identification

classification 💻 cs.CV
keywords networkdeepencoderoutputreidinformationinputissue
0
0 comments X
read the original abstract

Most existing person re-identification (ReID) methods have good feature representations to distinguish pedestrians with deep convolutional neural network (CNN) and metric learning methods. However, these works concentrate on the similarity between encoder output and ground-truth, ignoring the correlation between input and encoder output, which affects the performance of identifying different pedestrians. To address this limitation, We design a Deep InfoMax (DIM) network to maximize the mutual information (MI) between the input image and encoder output, which doesn't need any auxiliary labels. To evaluate the effectiveness of the DIM network, we propose end-to-end Global-DIM and Local-DIM models. Additionally, the DIM network provides a new solution for cross-dataset unsupervised ReID issue as it needs no extra labels. The experiments prove the superiority of MI theory on the ReID issue, which achieves the state-of-the-art results.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.