OpenCodePapers

open-vocabulary-panoptic-segmentation-on-ade20k

Panoptic SegmentationOpen Vocabulary Panoptic Segmentation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodePQModelNameReleaseDate
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding✓ Link31.6UMG-CLIP-E/142024-01-12
PosSAM: Panoptic Open-vocabulary Segment Anything✓ Link29.2PosSAM2024-03-14
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding✓ Link29.1UMG-CLIP-L/142024-01-12
Mitigating Objectness Bias and Region-to-Text Misalignment for Open-Vocabulary Panoptic Segmentation✓ Link28.6OVRCOAT2026-03-22
Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation✓ Link27.1MAFT+2024-08-01
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP✓ Link26.8FC-CLIP2023-08-04
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction✓ Link23.7CLIPSelf2023-10-02
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models✓ Link23.4ODISE(Caption)2023-03-08
Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models✓ Link22.6ODISE (Label)2023-03-08
FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation16.3FreeSeg2023-03-30
Extract Free Dense Labels from CLIP✓ Link15.1MaskCLIP2021-12-02
Check out how to contribute new results. Then edit this file on GitLab or GitHub.