Semantic Segmentation On Deliver

Métriques

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mIoU	Paper Title
StitchFusion(RGB-D-E-LiDAR)	68.18	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
StitchFusion (RGB-LiDAR)	58.03	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
CMX (RGB-Depth)	62.67	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
TokenFusion (RGB-Depth)	60.25	Multimodal Token Fusion for Vision Transformers
CMX (RGB-LiDAR)	56.37	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
StitchFusion (RGB-D-LiDAR)	66.65	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
MemorySAM-B+(RGB)	53.22	MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
StitchFusion (RGB-Event)	57.44	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
GeminiFusion	66.9	GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
HRFuser (RGB-D-E-Li)	52.97	HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
StitchFusion (RGB-Depth)	65.75	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
MemorySAM-B+(R-D-E-L)	65.38	MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
HRFuser (RGB-D-Event)	51.83	HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
HRFuser (RGB-Depth)	51.88	HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
MemorySAM-B+(R-D-E)	62.42	MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
CMX (RGB-Event)	56.52	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
MemorySAM-B+(R-D)	63.48	MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
TokenFusion (RGB-Event)	45.63	Multimodal Token Fusion for Vision Transformers
CMNeXt (RGB-D-E-LiDAR)	66.30	Delivering Arbitrary-Modal Semantic Segmentation
CAFuser-CAA	68.6	CAFuser: Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes

0 of 26 row(s) selected.