# Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks

Source: [Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks](<https://www.sota2.com/research/paper/68fa6da91e209131cea3b3e7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-14T18:41:08.031Z

Authors: Miquel Mart\\'i i Rabad\\'an, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki

Published: 2022-10-18T15:02:51.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2210.09919>)

[PDF](<https://arxiv.org/pdf/2210.09919.pdf>)