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

English

Semantic Segmentation On Zju Rgb P

Metrics

Frame (fps)

mIoU

Results

Performance results of various models on this benchmark

Model Name	Frame (fps)	mIoU	Paper Title	Repository
CSFNet-2	75 (3090)	91.40	CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes	-
RoadFormer+ (ConvNeXt-L, RGB-AoLP)	-	93.0	RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion	-
SwiftNet (RGB)	-	80.3	In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
RoadFormer+ (ConvNeXt-B, RGB-AoLP)	-	92.9	RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion	-
ShareCMP (B2 RGB-FP)	-	92.4	ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
ShareCMP (B4 RGB-FP)	-	92.7	ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
EAFNet (RGB-DoLP)	-	85.4	Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion
SegFormer-B2 (RGB)	-	89.6	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
EAFNet (RGB-AoLP)	-	85.7	Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion
CSFNet-1	108.5	90.85	CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes	-
EAFNet (3Path)	-	83.4	Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion
CMX (B4 RGB-AoLP)	-	92.6	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
CMX (B2 RGB-DoLP)	-	92.2	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers

0 of 13 row(s) selected.