Journal
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
Volume 18, Issue 4, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3501405
Keywords
Person re-identification; pooling strategy; attention mechanism; triplet loss
Categories
Funding
- National Key R&D Program of China [2020YFC1523202]
Ask authors/readers for more resources
This article proposes a novel harmonious multi-branch network (HMBN) to address issues in person re-identification. HMBN learns pedestrian information using different stripes on different branches and solves intra-branch and inter-branch problems through horizontal overlapped partitioning and attention mechanism. Experimental results demonstrate the superiority of HMBN over other methods.
Recently, advances in person re-identification (Re-ID) has benefitted from use of the popular multi-branch network. However, performing feature learning in a single branch with uniform partitioning is likely to separate meaningful local regions, and correlation among different branches is not well established. In this article, we propose a novel harmonious multi-branch network (HMBN) to relieve these intra-branch and inter-branch problems harmoniously. HMBN is a multi-branch network with various stripes on different branches to learn coarse-to-fine pedestrian information. We first replace the uniform partition with a horizontal overlapped partition to cover meaningful local regions between adjacent stripes in a single branch. We then incorporate a novel attention module to make all branches interact by modeling spatial contextual dependencies across branches. Finally, in order to train the HMBN more effectively, a harder triplet loss is introduced to optimize triplets in a harder manner. Extensive experiments are conducted on three benchmark datasets - DukeMTMC-reID, CUHK03, and Market-1501 - demonstrating the superiority of our proposed HMBN over state-of-the-art methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available