Semantic Segmentation On Trans10K

Métriques

GFLOPs

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
DANet	198.00	Dual Attention Network for Scene Segmentation
PSPNet	187.03	Pyramid Scene Parsing Network
U-Net	124.55	U-Net: Convolutional Networks for Biomedical Image Segmentation
Trans2Lab	61.31	Segmenting Transparent Objects in the Wild
Trans2Seg	49.03	Segmenting Transparent Object in the Wild with Transformer
RefineNet	44.56	RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
OCNet	43.31	OCNet: Object Context Network for Scene Parsing
FCN	42.23	Fully Convolutional Networks for Semantic Segmentation
DeepLabV3+	37.98	Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
DenseASPP	36.20	DenseASPP for Semantic Segmentation in Street Scenes
Trans4Trans (M)	34.38	Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World
Trans4Trans (S)	19.92	Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World
BiSeNet	19.91	BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
ICNet	10.64	ICNet for Real-Time Semantic Segmentation on High-Resolution Images
Trans4Trans (T)	10.45	Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World

0 of 15 row(s) selected.