Unsupervised Graph Association for Person Re-Identification
Lists
Only you see this
Abstract
In this paper, we propose an unsupervised graph association (UGA) framework to learn the underlying view-invariant representations from the video pedestrian tracklets. The core points of UGA are mining the underlying cross-view associations and reducing the damage of noise associations. To this end, UGA is adopts a two-stage training strategy: (1) intra-camera learning stage and (2) intercamera learning stage. The former learns the intra-camera representation for each camera. While the latter builds a cross-view graph (CVG) to associate different cameras. By doing this, we can learn view-invariant representation for all person. Extensive experiments and ablation studies on seven re-id datasets demonstrate the superiority of the proposed UGA over most state-of-the-art unsupervised and domain adaptation re-id methods.
BibTeX
@inproceedings{wu2019unsupervised,
author = {Jinlin Wu and Hao Liu and Yang Yang and Zhen Lei and Shengcai Liao and Stan Z. Li},
title = {{Unsupervised Graph Association for Person Re-Identification}},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/iccv.2019.00841},
}Loading related content...