Semi-supervised learning 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 significant 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 photometric component. Experiments with additional data from the large coarsely annotated subset of Cityscapes suggest that semi-supervised training can outperform supervised training with the coarse labels.
翻译:在实际部署深层模型方面,半监督的半监督学习有吸引力的技术,因为它放松了对标签数据的依赖。在密集的预测范围中,这一点特别重要,因为像素级的批注需要大量努力。本文考虑了对受扰动的无标签投入进行一致预测的半监督算法。我们研究的是,在两个模型中,只有两个模型中有一个实例受到扰动,防止通过未受扰动的场景向后传的优点。我们还提出一个竞争性的扰动模型,作为几何扭曲和光度振荡的构成。我们试验高效模型,因为它们对实时应用和低功率应用的重要性。我们的实验显示了以下明显的优势:(1)单向一致性,(2)只对学生分支进行扰动,(3)强光度和几何性扰动。我们的扰动模型超越了最近的工作,大部分贡献来自光度部分。我们用大量粗糙的城市景景区进行的额外数据进行的实验表明,半监督培训可以超过以粗皮标签进行的监督培训。