Naslov
Revisiting Consistency for Semi-Supervised Semantic Segmentation

Autori
Grubišić, Ivan ; Oršić, Marin ; Šegvić, Siniša

Izvornik
Sensors (1424-8220) 23 (2023), 2; 1-26

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
semi-supervised learning ; semantic segmentation ; dense prediction ; one-way consistency ; deep learning ; scene understanding

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA