HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Zero Shot Semantic Segmentation On Pascal Voc

평가 지표

Inductive Setting hIoU
Transductive Setting hIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Inductive Setting hIoU
Transductive Setting hIoU
Paper TitleRepository
CLIP-RC88.493.0Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation
MaskCLIP+-87.4Extract Free Dense Labels from CLIP
ZegCLIP84.391.1ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
DeOp80.8-Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network
SPNet-38.8Semantic Projection Network for Zero- and Few-Label Semantic Segmentation
CaGNet-43.7Context-aware Feature Generation for Zero-shot Semantic Segmentation
OTSeg84.594.2OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
FreeSeg-86.9FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation-
OTSeg+87.494.4OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
zsseg77.579.3A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
ZegFormer73.3-Decoupling Zero-Shot Semantic Segmentation
ZS5-33.8Zero-Shot Semantic Segmentation
STRICT-49.8A Closer Look at Self-training for Zero-Label Semantic Segmentation
0 of 13 row(s) selected.