Open Vocabulary Panoptic Segmentation On

Results

Performance results of various models on this benchmark

		Paper Title
PosSAM	29.2	PosSAM: Panoptic Open-vocabulary Segment Anything
MAFT+	27.1	Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
FC-CLIP	26.8	Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
CLIPSelf	23.7	CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
ODISE(Caption)	23.4	Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
ODISE (Label)	22.6	Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
FreeSeg	16.3	FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation
MaskCLIP	15.1	Extract Free Dense Labels from CLIP

0 of 8 row(s) selected.