icon-cookie
The website uses cookies to optimize your user experience. Using this website grants us the permission to collect certain information essential to the provision of our services to you, but you may change the cookie settings within your browser any time you wish. Learn more
I agree
blank_error__heading
blank_error__body
Text direction?

ICCV 2019 Open Access Repository

Instance-Guided Context Rendering for Cross-Domain Person Re-Identification
Yanbei Chen, Xiatian Zhu, Shaogang Gong; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 232-242
Abstract
Existing person re-identification (re-id) methods mostly assume the availability of large-scale identity labels for model learning in any target domain deployment. This greatly limits their scalability in practice. To tackle this limitation, we propose a novel Instance-Guided Context Rendering scheme, which transfers the source person identities into diverse target domain contexts to enable supervised re-id model learning in the unlabelled target domain. Unlike previous image synthesis methods that transform the source person images into limited fixed target styles, our approach produces more visually plausible, and diverse synthetic training data. Specifically, we formulate a dual conditional generative adversarial network that augments each source person image with rich contextual variations. To explicitly achieve diverse rendering effects, we leverage abundant unlabelled target instances as contextual guidance for image generation. Extensive experiments on Market-1501, DukeMTMC-reID and CUHK03 benchmarks show that the re-id performance can be significantly improved when using our synthetic data in cross-domain re-id model learning.
Related Material

[pdf] [supp]
[bibtex]
@InProceedings{Chen_2019_ICCV,
author = {Chen, Yanbei and Zhu, Xiatian and Gong, Shaogang},
title = {Instance-Guided Context Rendering for Cross-Domain Person Re-Identification},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}
Measure
Measure
Related Notes
Get a free MyMarkup account to save this article and view it later on any device.
Create account

End User License Agreement

Summary | 2 Annotations
Existing person re-identification (re-id) methods mostly assume the availability of large-scale identity labels for model learning in any target domain deployment. This greatly limits their scalability in pr
2020/09/16 06:36
endering scheme, which transfers the source person identities into diverse target domain contexts to enable supervised re-id model learning in the unlabelled target domain. Unlike previous image synthesis methods that transf
2020/09/16 06:36