REVIEW 4 cited by
A Survey on Semi-Supervised Semantic Segmentation
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
read the original abstract
Semantic segmentation is one of the most challenging tasks in computer vision. However, in many applications, a frequent obstacle is the lack of labeled images, due to the high cost of pixel-level labeling. In this scenario, it makes sense to approach the problem from a semi-supervised point of view, where both labeled and unlabeled images are exploited. In recent years this line of research has gained much interest and many approaches have been published in this direction. Therefore, the main objective of this study is to provide an overview of the current state of the art in semi-supervised semantic segmentation, offering an updated taxonomy of all existing methods to date. This is complemented by an experimentation with a variety of models representing all the categories of the taxonomy on the most widely used becnhmark datasets in the literature, and a final discussion on the results obtained, the challenges and the most promising lines of future research.
Forward citations
Cited by 4 Pith papers
-
SemiSegECG: A Multi-Dataset Benchmark for Semi-Supervised Semantic Segmentation in ECG Delineation
A new multi-dataset benchmark for semi-supervised ECG delineation reports that vision transformer backbones generally benefit more from semi-supervised training than a ResNet backbone.
-
RS-MTDF: Multi-Teacher Distillation and Fusion for Remote Sensing Semi-Supervised Semantic Segmentation
A multi-teacher framework distills frozen DINOv2 and CLIP features into a student model to improve low-label remote sensing segmentation.
-
Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness
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.
-
Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
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.
Discussion (0). Continue with ORCID to comment.