HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

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 Title	Repository
CLIP-RC	88.4	93.0	Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation	-
MaskCLIP+	-	87.4	Extract Free Dense Labels from CLIP
ZegCLIP	84.3	91.1	ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation
DeOp	80.8	-	Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network
SPNet	-	38.8	Semantic Projection Network for Zero- and Few-Label Semantic Segmentation	-
CaGNet	-	43.7	Context-aware Feature Generation for Zero-shot Semantic Segmentation
OTSeg	84.5	94.2	OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
FreeSeg	-	86.9	FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation	-
OTSeg+	87.4	94.4	OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
zsseg	77.5	79.3	A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
ZegFormer	73.3	-	Decoupling Zero-Shot Semantic Segmentation
ZS5	-	33.8	Zero-Shot Semantic Segmentation
STRICT	-	49.8	A Closer Look at Self-training for Zero-Label Semantic Segmentation

0 of 13 row(s) selected.