Papers › Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs

Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs

25 Jan 2024arXiv:2401.14387archive 2025-07-28

Michael R. H. Vorndran, Bernhard F. Roeck

Efficiently generating sufficient labeled data remains a major bottleneck in deep learning, particularly for image segmentation tasks where labeling requires significant time and effort. This study tackles this issue in a resource-constrained environment, devoid of extensive datasets or pre-existing models. We introduce Inconsistency Masks (IM), a novel approach that filters uncertainty in image-pseudo-label pairs to substantially enhance segmentation quality, surpassing traditional semi-supervised learning techniques. Employing IM, we achieve strong segmentation results with as little as 10% labeled data, across four diverse datasets and it further benefits from integration with other techniques, indicating broad applicability. Notably on the ISIC 2018 dataset, three of our hybrid approaches even outperform models trained on the fully labeled dataset. We also present a detailed comparative analysis of prevalent semi-supervised learning strategies, all under uniform starting conditions, to underline our approach's effectiveness and robustness. The full code is available at: https://github.com/MichaelVorndran/InconsistencyMasks

PaperPDFCode

Code

michaelvorndran/inconsistencymasks officialmentioned in papermentioned on GitHubtf 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

Image SegmentationLesion SegmentationMedical Image SegmentationPseudo LabelSegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationSemi-supervised Medical Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lesion Segmentation ISIC 2018 AIM++ (256x256, 1.5m parameters, 10% labeled data, no pretraining) mean Dice 0.85 #13 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 10% labeled IM++ (416x208, 2.7m parameters, no pretraining) Mean IoU (class) 0.428 #1 of 1 Archive leaderboard report
Semi-Supervised Semantic Segmentation SUIM AIM+ (256x256, 2.7m parameters, 10% labeled data, no pretraining) Mean IoU (class) 0.482 #1 of 1 Archive leaderboard report
Semi-supervised Medical Image Segmentation Lesion Segmentation on ISIC 2018 AIM++ (256x256, 1.5m parameters, 10% labeled data, no pretraining) Dice Score 0.85 #1 of 1 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.

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