We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations. We evaluate it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled data and ablate design choices and hyper-parameters. Dense FixMatch significantly improves results compared to supervised learning using only labeled data, approaching its performance with 1/4 of the labeled samples.
@article{arxiv.2210.09919,
title = {Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks},
author = {Miquel Martí i Rabadán and Alessandro Pieropan and Hossein Azizpour and Atsuto Maki},
journal= {arXiv preprint arXiv:2210.09919},
year = {2022}
}