SOTAVerified

Semi-Supervised Semantic Segmentation

Models that are trained with a small number of labeled examples and a large number of unlabeled examples and whose aim is to learn to segment an image (i.e. assign a class to every pixel).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 61–70 of 190 papers

TitleStatusHype
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory BankCode1
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
Bootstrapping Semantic Segmentation with Regional ContrastCode1
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic SegmentationCode1
Three Ways to Improve Semantic Segmentation with Self-Supervised Depth EstimationCode1
A Three-Stage Self-Training Framework for Semi-Supervised Semantic SegmentationCode1
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR SegmentationCode1
PseudoSeg: Designing Pseudo Labels for Semantic SegmentationCode1
ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised LearningCode1
Part-aware Prototype Network for Few-shot Semantic SegmentationCode1
Show:102550
← PrevPage 7 of 19Next →

No leaderboard results yet.