Zero-Guidance Segmentation

1 papers with code • 0 benchmarks • 0 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

Most implemented papers

Zero-guidance Segmentation Using Zero Segment Labels

nessessence/ZeroGuidanceSeg ICCV 2023

CLIP has enabled new and exciting joint vision-language applications, one of which is open-vocabulary segmentation, which can locate any segment given an arbitrary text query.