REVIEW 2 cited by
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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.
Forward citations
Cited by 2 Pith papers
-
Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions
Hierarchical task tokens discover feature- and prediction-level pseudo supervision, improving partially annotated multi-task dense prediction.
-
AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning
A FixMatch-based binary classifier with active learning finds rare image anomalies starting from 5-10 labelled examples, with AUROC up to 0.96 on miniImageNet and 0.89 on GalaxyMNIST.
Discussion (0). Continue with ORCID to comment.