Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation [article]

Zhiyuan Liang, Tiancai Wang, Xiangyu Zhang, Jian Sun, Jianbing Shen
<span title="2022-03-22">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained (i.e., point-, scribble-, and block-wise) supervisions, where only a small proportion of pixels are labeled in each image. In this paper, we propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels. The tree energy loss represents images as minimum spanning trees to model both low-level and high-level pair-wise affinities. By sequentially applying these
more &raquo; ... finities to the network prediction, soft pseudo labels for unlabeled pixels are generated in a coarse-to-fine manner, achieving dynamic online self-training. The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss. Compared with previous SASS methods, our method requires no multistage training strategies, alternating optimization procedures, additional supervised data, or time-consuming post-processing while outperforming them in all SASS settings. Code is available at https://github.com/megvii-research/TreeEnergyLoss.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.10739v2">arXiv:2203.10739v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mmh6z5d62fg75e6jzlifpeieom">fatcat:mmh6z5d62fg75e6jzlifpeieom</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220324101112/https://arxiv.org/pdf/2203.10739v2.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/2d/b0/2db08db367f99e61d1946f61fa98be0498df828e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.10739v2" 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>