Semi-Supervised Semantic Segmentation
45개 벤치마크 · 논문 205편 · 이 태스크의 논문 보기 →
Benchmarks
Cityscapes 12.5% labeled
Cityscapes 25% labeled
PASCAL VOC 2012 25% labeled
Cityscapes 50% labeled
Cityscapes 6.25% labeled
PASCAL VOC 2012 1464 labels
PASCAL VOC 2012 92 labeled
PASCAL VOC 2012 183 labeled
PASCAL VOC 2012 732 labeled
PASCAL VOC 2012 366 labeled
PASCAL VOC 2012 50%
Pascal VOC 2012 5% labeled
Pascal VOC 2012 2% labeled
SemanticKITTI
nuScenes
COCO 1/128 labeled
COCO 1/256 labeled
COCO 1/64 labeled
ScribbleKITTI
COCO 1/512 labeled
COCO 1/32 labeled
Pascal VOC 2012 1% labeled
ADE20K 1/16 labeled
ADE20K 1/32 labeled
Cityscapes 2% labeled
Cityscapes 5% labeled
Cityscapes 93 labeled
Stanford 2D-3D
WoodScape
2D-3D-S
Cityscapes 10% labeled
KiTS19
Kvasir-Instrument
SUIM
Most implemented
Adversarial Learning for Semi-Supervised Semantic Segmentation
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers
Semi-Supervised Semantic Segmentation with Cross-Consistency Training
Semi-supervised semantic segmentation needs strong, varied perturbations
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
Papers
Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank
Although semi-supervised semantic segmentation ($\text{S}^4$) utilizes abundant unlabeled data to reduce manual labeling burdens, independent training of labeled and unlabeled data causes the former to dominate, which se…
Semi-Supervised Semantic SegmentationCW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers
Semi-supervised semantic segmentation has long turned on one question, which pseudo-labels to trust, and a generation of selection rules, dynamic thresholds, per-class curricula, soft confidence weights, answered it for …
Semi-Supervised Semantic SegmentationPixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation
Semi-supervised semantic segmentation (SSSS) has long turned on one question, which pseudo-labels to trust, and answered it with ever more careful confidence filtering. Foundation backbones change the regime: with a DINO…
Semi-Supervised Semantic SegmentationContrastive LearningBidirectional Fusion Guided by Cardiac Patterns for Semi-Supervised ECG Segmentation
Accurate delineation of electrocardiogram (ECG), the segmentation of meaningful waveform features, is crucial for cardiovascular diagnostics. However, the scarcity of annotated data poses a significant challenge for trai…
Semi-Supervised Semantic SegmentationUniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation
Semi-supervised semantic segmentation in computational pathology remains challenging due to scarce pixel-level annotations and unreliable pseudo-label supervision. We propose UniSemAlign, a dual-modal semantic alignment …
Semi-Supervised Semantic SegmentationVision-Language Model Purified Semi-Supervised Semantic Segmentation for Remote Sensing Images
The semi-supervised semantic segmentation (S4) can learn rich visual knowledge from low-cost unlabeled images. However, traditional S4 architectures all face the challenge of low-quality pseudo-labels, especially for the…
Semi-Supervised Semantic Segmentation