Learning from Pixel-Level Noisy Label : A New Perspective for Light Field Saliency Detection [article]

Mingtao Feng, Kendong Liu, Liang Zhang, Hongshan Yu, Yaonan Wang, Ajmal Mian
<span title="2022-04-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Saliency detection with light field images is becoming attractive given the abundant cues available, however, this comes at the expense of large-scale pixel level annotated data which is expensive to generate. In this paper, we propose to learn light field saliency from pixel-level noisy labels obtained from unsupervised hand crafted featured based saliency methods. Given this goal, a natural question is: can we efficiently incorporate the relationships among light field cues while identifying
more &raquo; ... lean labels in a unified framework? We address this question by formulating the learning as a joint optimization of intra light field features fusion stream and inter scenes correlation stream to generate the predictions. Specially, we first introduce a pixel forgetting guided fusion module to mutually enhance the light field features and exploit pixel consistency across iterations to identify noisy pixels. Next, we introduce a cross scene noise penalty loss for better reflecting latent structures of training data and enabling the learning to be invariant to noise. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our framework showing that it learns saliency prediction comparable to state-of-the-art fully supervised light field saliency methods. Our code is available at https://github.com/OLobbCode/NoiseLF.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.13456v1">arXiv:2204.13456v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/np3aj7mzingu3gt46zwym5emha">fatcat:np3aj7mzingu3gt46zwym5emha</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220503021956/https://arxiv.org/pdf/2204.13456v1.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/54/3f/543fb01c419fc1c444eba8ac1f9e34599d833366.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.13456v1" 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>