Self-paced and self-consistent co-training for semi-supervised image segmentation

Ping Wang; Jizong Peng; Marco Pedersoli; Yuanfeng Zhou; Caiming Zhang; Christian Desrosiers

Self-paced and self-consistent co-training for semi-supervised image segmentation [article]

Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers

<span title="2021-02-10">2021</span> <i > arXiv </i>   <span class="release-stage" >pre-print</span>

Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent co-training method. To help distillate information from unlabeled images, we first design a self-paced learning strategy for co-training that lets jointly-trained neural networks focus on easier-to-segment regions first, and then gradually consider harder

more »

... .This is achieved via an end-to-end differentiable loss inthe form of a generalized Jensen Shannon Divergence(JSD). Moreover, to encourage predictions from different networks to be both consistent and confident, we enhance this generalized JSD loss with an uncertainty regularizer based on entropy. The robustness of individual models is further improved using a self-ensembling loss that enforces their prediction to be consistent across different training iterations. We demonstrate the potential of our method on three challenging image segmentation problems with different image modalities, using small fraction of labeled data. Results show clear advantages in terms of performance compared to the standard co-training baselines and recently proposed state-of-the-art approaches for semi-supervised segmentation

<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.00325v4">arXiv:2011.00325v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xzprv3daabhlfeuzr4o2zraakq">fatcat:xzprv3daabhlfeuzr4o2zraakq</a> </span>

<span class="ui label basic blue small">Multiple Versions</span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210220053427/https://arxiv.org/pdf/2011.00325v4.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/b0/ee/b0ee2c4f65b3f7e65f4b97fc07eefde38e50b225.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.00325v4" 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>

Self-paced and self-consistent co-training for semi-supervised image segmentation [article]

Preserved Fulltext

Other Versions