Semantic Segmentation On Pascal Context

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
VPNeXt	71.1	VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer	-
PlainSeg (EVA-02-L)	71.0	Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers
InternImage-H	70.3	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
RSSeg-ViT-L (BEiT pretrain)	68.9	Representation Separation for Semantic Segmentation with Vision Transformers	-
ViT-Adapter-L (Mask2Former, BEiT pretrain)	68.2	Vision Transformer Adapter for Dense Predictions
ViT-Adapter-L (UperNet, BEiT pretrain)	67.5	Vision Transformer Adapter for Dense Predictions
RSSeg-ViT-L	67.5	Representation Separation for Semantic Segmentation with Vision Transformers	-
SegViT (ours)	65.3	SegViT: Semantic Segmentation with Plain Vision Transformers
CAA + CAR (ConvNeXt-Large + JPU)	64.1	CAR: Class-aware Regularizations for Semantic Segmentation
SenFormer (Swin-L)	64.0	Efficient Self-Ensemble for Semantic Segmentation
Sequential Ensemble (Segformer + HRNet)	62.1	Sequential Ensembling for Semantic Segmentation	-
CAA + Simple decoder (Efficientnet-B7)	60.5	Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
DPT-Hybrid	60.46	Vision Transformers for Dense Prediction
CAA (Efficientnet-B7)	60.1	Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
HRNetV2 + OCR + RMI (PaddleClas pretrained)	59.6	Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
Seg-L-Mask/16	59.0	Segmenter: Transformer for Semantic Segmentation
ResNeSt-269	58.9	ResNeSt: Split-Attention Networks
DEPICT-SA (ViT-L multi-scale)	58.6	Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective
ResNeSt-200	58.4	ResNeSt: Split-Attention Networks
DEPICT-SA (ViT-L single-scale)	57.9	Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective

0 of 66 row(s) selected.