Semantic Segmentation On Coco Stuff Test

Métriques

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mIoU	Paper Title	Repository
CAA (ResNet-101)	41.2%	Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
SenFormer (Swin-L)	50.1%	Efficient Self-Ensemble for Semantic Segmentation
DRAN(ResNet-101)	41.2%	Scene Segmentation with Dual Relation-aware Attention Network
CCL (ResNet-101)	35.7%	Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation
OCR (ResNet-101)	39.5%	Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
DAG-RNN (VGG-16)	31.2%	DAG-Recurrent Neural Networks For Scene Labeling	-
FCN (VGG-16)	22.7%	Fully Convolutional Networks for Semantic Segmentation
OCR (HRNetV2-W48)	40.5%	Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
VPNeXt	53.7	VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer	-
EVA	53.4%	EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
SegViT (ours)	50.3%	SegViT: Semantic Segmentation with Plain Vision Transformers
EMANet	39.9%	Expectation-Maximization Attention Networks for Semantic Segmentation
RSSeg-ViT-L	52.0%	Representation Separation for Semantic Segmentation with Vision Transformers	-
DANet (ResNet-101)	39.7%	Dual Attention Network for Scene Segmentation
SVCNet (ResNet-101)	39.6%	Semantic Correlation Promoted Shape-Variant Context for Segmentation
RSSeg-ViT-L (BEiT pretrain)	52.6%	Representation Separation for Semantic Segmentation with Vision Transformers	-
RefineNet (ResNet-101)	33.6%	RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
CAA (Efficientnet-B7)	45.4%	Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
HRNetV2 + OCR + RMI (PaddleClas pretrained)	45.2%	Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
Asymmetric ALNN	37.2%	Asymmetric Non-local Neural Networks for Semantic Segmentation

0 of 20 row(s) selected.