Papers › Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs
Inconsistency Masks: Removing the Uncertainty from Input-Pseudo-Label Pairs
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
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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