computer-vision-1
Zero-Guidance Segmentation
3260 papers • 126 benchmarks • 313 datasets
The task aiming to discover semantic segments without any user guidance in the form of text queries or predefined classes, and label them using natural language automatically
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in zero-guidance-segmentation-1
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find zero-guidance-segmentation-1 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.
Most implemented papers
Zero-guidance Segmentation Using Zero Segment Labels
Supasorn Suwajanakorn, Pitchaporn Rewatbowornwong, Nattanat Chatthee, Ekapol Chuangsuwanich•Wed Mar 22 2023
This research proposes a novel problem zero-guidance segmentation and the first baseline that leverages two pre-trained generalist models, DINO and CLIP, to solve this problem without any fine-tuning or segmentation dataset.
18