Naslov
A baseline for semi-supervised learning of efficient semantic segmentation models

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

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of MVA 2021 - 17th International Conference on Machine Vision Applications / - , 2021, 1-5

Skup
17th International Conference on Machine Vision Applications (MVA 2021)

Mjesto i datum
Okazaki, Japan, 25.07.2021. - 27.07.2021

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
computer vision ; semantic segmentation ; semi-supervised learning

Sažetak
Semi-supervised learning is especially interesting in the dense prediction context due to high cost of pixel-level ground truth. Unfortunately, most such approaches are evaluated on outdated architectures which hamper research due to very slow training and high requirements on GPU RAM. We address this concern by presenting a simple and effective baseline which works very well both on standard and efficient architectures. Our baseline is based on one-way consistency and nonlinear geometric and photometric perturbations. We show advantage of perturbing only the student branch and present a plausible explanation of such behaviour. Experiments on Cityscapes and CIFAR-10 demonstrate competitive performance with respect to prior work.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA