Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy [article]

Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Samar M Alsaleh, Robby T Tan, Carola-Bibiane Schönlieb
<span title="2021-10-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has motivated the fast development of semi-supervised techniques, whose performance is on a par with or better than supervised approaches. A current major challenge for semi-supervised techniques is how to better handle the network calibration and confirmation bias problems for improving performance. In this work, we argue
more &raquo; ... that energy models are an effective alternative to such problems. With this motivation in mind, we propose a hybrid framework for semi-supervised classification called CREPE model (1-Lapla𝐂ian g𝐑aph 𝐄nergy for 𝐏seudo-lab𝐄ls). Firstly, we introduce a new energy model based on the non-smooth ℓ_1 norm of the normalised graph 1-Laplacian. Our functional enforces a sufficiently smooth solution and strengthens the intrinsic relation between the labelled and unlabelled data. Secondly, we provide a theoretical analysis for our proposed scheme and show that the solution trajectory does converge to a non-constant steady point. Thirdly, we derive the connection of our energy model for pseudo-labelling. We show that our energy model produces more meaningful pseudo-labels than the ones generated directly by a deep network. We extensively evaluate our framework, through numerical and visual experiments, using six benchmarking datasets for natural and medical images. We demonstrate that our technique reports state-of-the-art results for semi-supervised classification.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.08635v4">arXiv:1906.08635v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hmfiiq3dbrapfiowpvfit22gna">fatcat:hmfiiq3dbrapfiowpvfit22gna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321091457/https://arxiv.org/pdf/1906.08635v3.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.08635v4" 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>