HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Semantic Segmentation On Pascal Context

Metrics

mIoU

Results

Performance results of various models on this benchmark

Paper Title
VPNeXt71.1VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer
PlainSeg (EVA-02-L)71.0Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers
InternImage-H70.3InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
RSSeg-ViT-L (BEiT pretrain)68.9Representation Separation for Semantic Segmentation with Vision Transformers
ViT-Adapter-L (Mask2Former, BEiT pretrain)68.2Vision Transformer Adapter for Dense Predictions
ViT-Adapter-L (UperNet, BEiT pretrain)67.5Vision Transformer Adapter for Dense Predictions
RSSeg-ViT-L67.5Representation Separation for Semantic Segmentation with Vision Transformers
SegViT (ours)65.3SegViT: Semantic Segmentation with Plain Vision Transformers
CAA + CAR (ConvNeXt-Large + JPU)64.1CAR: Class-aware Regularizations for Semantic Segmentation
SenFormer (Swin-L)64.0Efficient Self-Ensemble for Semantic Segmentation
Sequential Ensemble (Segformer + HRNet)62.1Sequential Ensembling for Semantic Segmentation
CAA + Simple decoder (Efficientnet-B7)60.5Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
DPT-Hybrid60.46Vision Transformers for Dense Prediction
CAA (Efficientnet-B7)60.1Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation
HRNetV2 + OCR + RMI (PaddleClas pretrained)59.6Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
Seg-L-Mask/1659.0Segmenter: Transformer for Semantic Segmentation
ResNeSt-26958.9ResNeSt: Split-Attention Networks
DEPICT-SA (ViT-L multi-scale)58.6Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective
ResNeSt-20058.4ResNeSt: Split-Attention Networks
DEPICT-SA (ViT-L single-scale)57.9Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective
0 of 66 row(s) selected.