HyperAI초신경

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

한국어

HyperAI초신경

Semantic Segmentation On Bjroad

평가 지표

IoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	IoU	Paper Title	Repository
CMMPNe	62.85	Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction	-
Res-UNet	54.24	Road Extraction by Deep Residual U-Net
D-LinkNet	57.96	D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction	-
SA-Gate	62.14	Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
CMNeXt	63.22	Delivering Arbitrary-Modal Semantic Segmentation
CMX	62.28	CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers
DeepDualMapper	60.19	DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories	-
DeepLabv3+	50.81	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
LinkNet	57.89	LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation
UNet	54.88	U-Net: Convolutional Networks for Biomedical Image Segmentation
Sun et al.	59.18	Leveraging Crowdsourced GPS Data for Road Extraction from Aerial Imagery	-

0 of 11 row(s) selected.