HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Open Vocabulary Panoptic Segmentation On

평가 지표

PQ

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
PQ
Paper TitleRepository
PosSAM29.2PosSAM: Panoptic Open-vocabulary Segment Anything
ODISE (Label)22.6Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
ODISE(Caption)23.4Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models
MAFT+27.1Collaborative Vision-Text Representation Optimizing for Open-Vocabulary Segmentation
MaskCLIP15.1Extract Free Dense Labels from CLIP
CLIPSelf23.7CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction-
FreeSeg16.3FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation-
FC-CLIP26.8Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP
0 of 8 row(s) selected.