Pith. sign in

REVIEW 5 cited by

Semi-supervised semantic segmentation needs strong, varied perturbations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 1906.01916 v5 pith:GT2KW7AR submitted 2019-06-05 cs.CV

Geoff French , Samuli Laine , Timo Aila , Michal Mackiewicz , Graham Finlayson This is my paper · ORCID
classification cs.CV
keywords segmentationsemi-supervisedsemanticregionsaugmentationchallengingclassdensity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists of uniform class clusters of samples separated by low density regions - as important to its success. We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of success. We then identify choice of augmentation as key to obtaining reliable performance without such low-density regions. We find that adapted variants of the recently proposed CutOut and CutMix augmentation techniques yield state-of-the-art semi-supervised semantic segmentation results in standard datasets. Furthermore, given its challenging nature we propose that semantic segmentation acts as an effective acid test for evaluating semi-supervised regularizers. Implementation at: https://github.com/Britefury/cutmix-semisup-seg.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A new harmonic-mean metric, RSS, combines mIoU, calibration error, and two uncertainty-quality measures, and is used to show that SSL segmentation models like UniMatchV2 sacrifice reliability for accuracy.

  2. Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    ASAug uses entropy-adaptive rotation and translation as strong augmentations in a teacher-student consistency framework, improving semi-supervised semantic segmentation by 0.5 to 4 mIoU on three benchmarks.

  3. P3Net: Progressive and Periodic Perturbation for Semi-Supervised Medical Image Segmentation

    eess.IV 2025-05 conditional novelty 5.0 of 10

    A progressive, periodic interpolation schedule and a boundary-focused loss improve semi-supervised medical image segmentation on four standard datasets.

  4. Augment to Segment: Tackling Pixel-Level Imbalance in Wheat Disease and Pest Segmentation

    cs.CV 2025-09 conditional novelty 4.0 of 10

    RPCP, a copy-paste augmentation with a random-convolution refinement, improves segmentation of rare insect damage in wheat leaves while leaving common-class accuracy roughly unchanged.

  5. FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation

    cs.CV 2025-06 conditional novelty 3.0 of 10

    FARCLUSS is a semi-supervised segmentation method that blends fuzzy pseudo-labels, uncertainty weighting, class rebalancing, and contrastive prototypes, with modest benchmark gains.

Pith tools