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

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

18 Oct 2022arXiv:2210.09919archive 2025-07-28

Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour, Atsuto Maki

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.

PaperPDFCode

Code

miquelmarti/DenseFixMatch officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationSemantic SegmentationSemi-Supervised Semantic Segmentationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled Dense FixMatch (DeepLabv3+ ResNet-101, uniform sampling, single pass eval) Validation mIoU 73.91% #20 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled Dense FixMatch (DeepLabv3+ ResNet-50, uniform sampling, single pass eval) Validation mIoU 73.39% #21 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) Validation mIoU 71.1% #15 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled Dense FixMatch (DeepLabv3+ ResNet-50, uniform sampling, single pass eval) Validation mIoU 70.65% #16 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 93 labeled Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) Validation mIoU 66.97 #2 of 3 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 93 labeled Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single-pass eval) Validation mIoU 65.81 #3 of 3 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes with extra (no coarse labels) Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) Validation mIoU 80.82 #1 of 2 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes with extra (no coarse labels) Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) Validation mIoU 79.98 #2 of 2 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) Validation mIoU 72.04 #26 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) Validation mIoU 69.02 #27 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 50% Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) Validation mIoU 74.73% #13 of 14 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 50% Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) Validation mIoU 71.69% #14 of 14 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) Validation mIoU 65.82% #36 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) Validation mIoU 62.49% #38 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval) Validation mIoU 54.85 #18 of 19 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled Dense FixMatch (DeepLabv3+ ResNet-50, over-sampling, single pass eval) Validation mIoU 52.15 #19 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

FixMatch

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections