A baseline for semi-supervised learning of efficient semantic segmentation models
| Autor: | Ivan Grubišić, Marin Oršić, Siniša Šegvić |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Ground truth
business.industry Computer science Context (language use) 02 engineering and technology Semi-supervised learning Machine learning computer.software_genre Semantics 01 natural sciences computer vision semantic segmentation semi-supervised learning Nonlinear system Consistency (database systems) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence 010306 general physics business Baseline (configuration management) computer |
| Zdroj: | MVA |
| DOI: | 10.23919/mva51890.2021.9511402 |
| Popis: | 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 Unfortunately, most such approaches are evaluated on outdated architectures which hamper research due to very slow training and high requirements on GPU RAM.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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|