unsupervised-semantic-segmentation
Unsupervised Semantic Segmentation with Language-image Pre-training
3260 papers • 126 benchmarks • 313 datasets
A segmentation task which does not utilise any human-level supervision for semantic segmentation except for a backbone which is initialised with features pre-trained with image-level labels.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in unsupervised-semantic-segmentation
Trend
Dataset
Best Model
Actions
Cityscapes val
Cityscapes val
ADE20K
ADE20K
COCO-Object
COCO-Object
Libraries
iUse these libraries to find unsupervised-semantic-segmentation models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
GroupViT: Semantic Segmentation Emerges from Text Supervision
X. Wang, Wonmin Byeon, Thomas Breuel, Jiarui Xu, Sifei Liu, Jan Kautz, Shalini De Mello•Mon Feb 21 2022
A hierarchical Grouping Vision Transformer (GroupViT), which goes beyond the regular grid structure representation and learns to group image regions into progressively larger arbitrary-shaped segments and performs competitively to state-of-the-art transfer-learning methods requiring greater levels of supervision.
641
