A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2012.09071v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
[article]
<span title="2021-03-30">2021</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2020-12-16">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.09071v1">arXiv:2012.09071v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/atwqlistdvgdbo2ilmpb3rns4q">fatcat:atwqlistdvgdbo2ilmpb3rns4q</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.09071v1">arXiv:2012.09071v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/atwqlistdvgdbo2ilmpb3rns4q">fatcat:atwqlistdvgdbo2ilmpb3rns4q</a> </span>
Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed versions) of an input. In this paper, we incorporate a Generative Adversarial Network (GAN) and a contrastive learning module into one joint training framework. While the GAN provides online data augmentation for contrastive learning, the contrastive module learns view-invariant features for generation. In this
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.09071v2">arXiv:2012.09071v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nsjt6bdjqjcgzpvfgvkjh3b27u">fatcat:nsjt6bdjqjcgzpvfgvkjh3b27u</a>
</span>
more »
... t, we propose a mesh-based view generator. Specifically, mesh projections serve as references towards generating novel views of a person. In addition, we propose a view-invariant loss to facilitate contrastive learning between original and generated views. Deviating from previous GAN-based unsupervised ReID methods involving domain adaptation, we do not rely on a labeled source dataset, which makes our method more flexible. Extensive experimental results show that our method significantly outperforms state-of-the-art methods under both, fully unsupervised and unsupervised domain adaptive settings on several large scale ReID datsets.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210401001536/https://arxiv.org/pdf/2012.09071v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/be/e3/bee39f695c4771fb761d614a1cd4e48ffa8fcc83.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.09071v2" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>