Multi-Source Domain Adaptation for Object Detection [article]

Xingxu Yao, Sicheng Zhao, Pengfei Xu, Jufeng Yang
<span title="2021-06-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that the labeled data are sampled from a single source domain, which ignores a more generalized scenario, where labeled data are from multiple source domains. For the more challenging task, we propose a unified Faster R-CNN based framework, termed Divide-and-Merge
more &raquo; ... Spindle Network (DMSN), which can simultaneously enhance domain invariance and preserve discriminative power. Specifically, the framework contains multiple source subnets and a pseudo target subnet. First, we propose a hierarchical feature alignment strategy to conduct strong and weak alignments for low- and high-level features, respectively, considering their different effects for object detection. Second, we develop a novel pseudo subnet learning algorithm to approximate optimal parameters of pseudo target subset by weighted combination of parameters in different source subnets. Finally, a consistency regularization for region proposal network is proposed to facilitate each subnet to learn more abstract invariances. Extensive experiments on different adaptation scenarios demonstrate the effectiveness of the proposed model.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15793v1">arXiv:2106.15793v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7bq2o3g6t5h73hd4oriwymgfem">fatcat:7bq2o3g6t5h73hd4oriwymgfem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210702013222/https://arxiv.org/pdf/2106.15793v1.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/3d/1a/3d1acd5ebed6e9e9f34ac1d88ac26405851bc58d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15793v1" 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>