Semantic Segmentation On Us3D

Metriken

mIoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
LMFNet-3	85.09	LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing
CMX	84.63	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
LMFNet-2	84.50	LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing
SA-Gate	83.62	Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
vFuseNet	83.53	Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks
SegFormer-B2	75.14	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
UNetFormer	74.77	UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
SegFormer-B1	74.19	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
PSNet	73.12	Pyramid Scene Parsing Network
FPN	72.51	Feature Pyramid Networks for Object Detection
SegFormer-B0	71.80	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

0 of 11 row(s) selected.

Semantic Segmentation On Us3D | SOTA | HyperAI