← Search

Feng Li*

1 accepted papers

2024

Segment and Recognize Anything at Any Granularity

ECCV 2024poster

"In this work, we introduce , an augmented image segmentation foundation for segmenting and recognizing anything at desired granularities. Compared to the foundational segmentation model SAM [?], our model has two unique advantages: (i) granularity-controllability in that the model can produce segme…

Cited by 214SourcePDFScholar