HyperAI超神経

プラットフォーム

Zero Shot Semantic Segmentation On Pascal Voc

評価指標

Inductive Setting hIoU

Transductive Setting hIoU

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

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

0 of 13 row(s) selected.

Zero Shot Semantic Segmentation On Pascal Voc | SOTA | HyperAI超神経