Grubišić Ivan, Oršić Marin, Šegvić Siniša
Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia.
Microblink Ltd., Strojarska Cesta 20, 10000 Zagreb, Croatia.
Sensors (Basel). 2023 Jan 13;23(2):940. doi: 10.3390/s23020940.
Semi-supervised learning is an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires substantial effort. This paper considers semi-supervised algorithms that enforce consistent predictions over perturbed unlabeled inputs. We study the advantages of perturbing only one of the two model instances and preventing the backward pass through the unperturbed instance. We also propose a competitive perturbation model as a composition of geometric warp and photometric jittering. We experiment with efficient models due to their importance for real-time and low-power applications. Our experiments show clear advantages of (1) one-way consistency, (2) perturbing only the student branch, and (3) strong photometric and geometric perturbations. Our perturbation model outperforms recent work and most of the contribution comes from the photometric component. Experiments with additional data from the large coarsely annotated subset of Cityscapes suggest that semi-supervised training can outperform supervised training with coarse labels. Our source code is available at https://github.com/Ivan1248/semisup-seg-efficient.
半监督学习在深度模型的实际部署中是一种颇具吸引力的技术，因为它减轻了对标记数据的依赖。在密集预测领域，这一点尤为重要，因为像素级标注需要大量精力。本文考虑了对半监督算法进行研究，这些算法对经过扰动的未标记输入强制进行一致预测。我们研究了仅对两个模型实例中的一个进行扰动并阻止反向传播通过未扰动实例的优势。我们还提出了一种竞争性扰动模型，它由几何扭曲和光度抖动组成。由于高效模型对实时和低功耗应用的重要性，我们对其进行了实验。我们的实验表明，（1）单向一致性、（2）仅扰动学生分支以及（3）强大的光度和几何扰动具有明显优势。我们的扰动模型优于近期的工作，并且大部分贡献来自光度组件。使用来自Cityscapes大型粗略标注子集的额外数据进行的实验表明，半监督训练可以优于使用粗略标签的监督训练。我们的源代码可在https://github.com/Ivan1248/semisup-seg-efficient获取。
