A baseline for semi-supervised learning of efficient semantic segmentation models (CROSBI ID 707247)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Grubišić, Ivan ; Oršić, Marin ; Šegvić, Siniša
engleski
A baseline for semi-supervised learning of efficient semantic segmentation models
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 Unfortunately, most such approaches are evaluated on outdated architectures which hamper research due to very slow training and high requirements on GPU RAM.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.
computer vision ; semantic segmentation ; semi-supervised learning
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1-5.
2021.
objavljeno
10.23919/mva51890.2021.9511402
Podaci o matičnoj publikaciji
Proceedings of MVA 2021 - 17th International Conference on Machine Vision Applications
Podaci o skupu
17th International Conference on Machine Vision Applications (MVA 2021)
poster
25.07.2021-27.07.2021
Okazaki, Japan