Crack Segmentation On Crackvision12K

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
Hybrid-Segmentor	0.62982	Hybrid-Segmentor: A Hybrid Approach to Automated Fine-Grained Crack Segmentation in Civil Infrastructure
UNet	0.60333	U-Net: Convolutional Networks for Biomedical Image Segmentation
FCN	0.59842	Fully Convolutional Networks for Semantic Segmentation
SegFormer	0.57969	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

0 of 4 row(s) selected.