Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Semantic Segmentation On Urbanlf

Metrics

mIoU (Real)

mIoU (Syn)

Results

Performance results of various models on this benchmark

Model Name	mIoU (Real)	mIoU (Syn)	Paper Title	Repository
DAVSS	75.91	74.27	Video Semantic Segmentation with Distortion-Aware Feature Correction
CMNeXt (RGB-LF33)	82.62	80.98	Delivering Arbitrary-Modal Semantic Segmentation
TMANet	77.14	76.41	Temporal Memory Attention for Video Semantic Segmentation
TDNet (ResNet-50)	76.48	74.71	Temporally Distributed Networks for Fast Video Semantic Segmentation
SETR (ViT-Large)	77.74	77.69	Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
SegFormer	82.20	78.53	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
OCR (HRNetV2-W48)	78.60	79.36	U-Net: Convolutional Networks for Biomedical Image Segmentation
CMNeXt (RGB-LF8)	83.22	80.74	Delivering Arbitrary-Modal Semantic Segmentation
CMNeXt (RGB-LF80)	83.11	81.02	Delivering Arbitrary-Modal Semantic Segmentation
SA-Gate	n.a.	79.53	Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
PSPNet	76.34	75.78	Pyramid Scene Parsing Network
ESANet	n.a.	79.43	Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis	-
MTINet (HRNetV2-W48)	n.a.	79.10	MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning
DeepLabV3+ (ResNet-101)	76.27	-	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

0 of 14 row(s) selected.