Check the preview of 2nd version of this platform being developed by the open MLCommons taskforce on automation and reproducibility as a free, open-source and technology-agnostic on-prem platform.

Diversity-Achieving Slow-DropBlock Network for Person Re-Identification

lib:9640c8a75eed3ee0 (v1.0.0)

Vote to reproduce this paper and share portable workflows   1 
Authors: Xiaofu Wu,Ben Xie,Shiliang Zhao,Suofei Zhang,Yong Xiao,Ming Li
ArXiv: 2002.04414
Document:  PDF  DOI 
Artifact development version: GitHub
Abstract URL: https://arxiv.org/abs/2002.04414v1


A big challenge of person re-identification (Re-ID) using a multi-branch network architecture is to learn diverse features from the ID-labeled dataset. The 2-branch Batch DropBlock (BDB) network was recently proposed for achieving diversity between the global branch and the feature-dropping branch. In this paper, we propose to move the dropping operation from the intermediate feature layer towards the input (image dropping). Since it may drop a large portion of input images, this makes the training hard to converge. Hence, we propose a novel double-batch-split co-training approach for remedying this problem. In particular, we show that the feature diversity can be well achieved with the use of multiple dropping branches by setting individual dropping ratio for each branch. Empirical evidence demonstrates that the proposed method performs superior to BDB on popular person Re-ID datasets, including Market-1501, DukeMTMC-reID and CUHK03 and the use of more dropping branches can further boost the performance.

Relevant initiatives  

Related knowledge about this paper Reproduced results (crowd-benchmarking and competitions) Artifact and reproducibility checklists Common formats for research projects and shared artifacts Reproducibility initiatives

Comments  

Please log in to add your comments!
If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!