Semantic Segmentation On Mcubes

Métriques

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mIoU	Paper Title	Repository
DRConv (RGB-A-D-N)	34.63%	Dynamic Region-Aware Convolution	-
StitchFusion (RGB-A)	52.68	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
DeepLabV3+ (RGB-A-D-N)	38.13%	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
StitchFusion (RGB-A-D-N)	53.92	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
ShareCMP (B2 RGB-A-D)	50.99%	ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
CMNeXt (B2 RGB-A-D-N)	51.54%	Delivering Arbitrary-Modal Semantic Segmentation
MMSFormer (RGB-A-D-N)	53.11%	MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
StitchFusion (RGB-N)	53.21	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
ShareCMP(B2 RGB-A)	50.34	ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
StitchFusion (RGB-A-D)	53.26	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
MMSFormer (RGB-A)	51.30%	MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
MemorySAM-B+(RGB-A-D)	52.20	MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation
MMSFormer (RGB)	50.44%	MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
MMSFormer (RGB-A-D)	52.05%	MMSFormer: Multimodal Transformer for Material and Semantic Segmentation
ShareCMP(B2 RGB-D)	50.55	ShareCMP: Polarization-Aware RGB-P Semantic Segmentation
DDF (RGB-A-D-N)	36.16%	Decoupled Dynamic Filter Networks
CMNeXt (B2 RGB-A-D)	49.48%	Delivering Arbitrary-Modal Semantic Segmentation
CMNeXt (B2 RGB-A)	48.42%	Delivering Arbitrary-Modal Semantic Segmentation
StitchFusion (RGB-D)	52.72	StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
MemorySAM-B+(RGB-A-D-N)	52.88	MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation

0 of 22 row(s) selected.