HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Semantic Segmentation On Vaihingen

평가 지표

mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	mIoU	Paper Title	Repository
CMX	82.87	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers	-
SegFormer-B0	75.57	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers	-
SA-Gate	81.03	Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
HRNet-48	76.75	Deep High-Resolution Representation Learning for Visual Recognition	-
SegFormer-B2	76.69	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers	-
UnetFormer	77.24	UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery	-
PSPNet	76.79	Pyramid Scene Parsing Network	-
LMFNet-2 (	82.49	LMFNet: An Efficient Multimodal Fusion Approach for Semantic Segmentation in High-Resolution Remote Sensing	-
V-FuseNet	79.56	Beyond RGB: Very High Resolution Urban Remote Sensing With Multimodal Deep Networks	-
SegFormer-B1	76.92	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers	-
DeepLabV3+	72.90	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation	-
HRNet-18	75.90	Deep High-Resolution Representation Learning for Visual Recognition	-
FPN	74.86	Feature Pyramid Networks for Object Detection	-

0 of 13 row(s) selected.