HyperAI

Semantic Segmentation On Deliver

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name
mIoU
Paper TitleRepository
StitchFusion(RGB-D-E-LiDAR)68.18StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
StitchFusion (RGB-LiDAR)58.03StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
CMX (RGB-Depth)62.67CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
TokenFusion (RGB-Depth)60.25Multimodal Token Fusion for Vision Transformers
CMX (RGB-LiDAR)56.37CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
StitchFusion (RGB-D-LiDAR)66.65StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
MemorySAM-B+(RGB)53.22MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
StitchFusion (RGB-Event)57.44StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
GeminiFusion66.9GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
HRFuser (RGB-D-E-Li)52.97HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
StitchFusion (RGB-Depth)65.75StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
MemorySAM-B+(R-D-E-L)65.38MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
HRFuser (RGB-D-Event)51.83HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
HRFuser (RGB-Depth)51.88HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
MemorySAM-B+(R-D-E)62.42MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
CMX (RGB-Event)56.52CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
MemorySAM-B+(R-D)63.48MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
TokenFusion (RGB-Event)45.63Multimodal Token Fusion for Vision Transformers
CMNeXt (RGB-D-E-LiDAR)66.30Delivering Arbitrary-Modal Semantic Segmentation
CAFuser-CAA68.6CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes
0 of 26 row(s) selected.