A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2004.00144v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
[article]
<span title="2020-03-31">2020</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Establishing dense semantic correspondences between object instances remains a challenging problem due to background clutter, significant scale and pose differences, and large intra-class variations. In this paper, we address weakly supervised semantic matching based on a deep network where only image pairs without manual keypoint correspondence annotations are provided. To facilitate network training with this weaker form of supervision, we 1) explicitly estimate the foreground regions to
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.00144v1">arXiv:2004.00144v1</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ompuspfmvel5jidmt7acev5ly">fatcat:6ompuspfmvel5jidmt7acev5ly</a>
</span>
more »
... ess the effect of background clutter and 2) develop cycle-consistent losses to enforce the predicted transformations across multiple images to be geometrically plausible and consistent. We train the proposed model using the PF-PASCAL dataset and evaluate the performance on the PF-PASCAL, PF-WILLOW, and TSS datasets. Extensive experimental results show that the proposed approach performs favorably against the state-of-the-art methods.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200403001504/https://arxiv.org/pdf/2004.00144v1.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]
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.00144v1" 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>