Real Time Semantic Segmentation On Camvid

Métriques

mIoU

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mIoU	Paper Title	Repository
EDANet	66.4	Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation	-
PP-LiteSeg-B	75	PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model	-
BiSeNet V2	72.4	BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation	-
BiSeNet V2-Large(Cityscapes-Pretrained)	78.5	BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation	-
BiSeNet V2-Large	73.2	BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation	-
TD4-PSP18	72.6	Temporally Distributed Networks for Fast Video Semantic Segmentation	-
BiSeNet V2(Cityscapes-Pretrained)	76.7	BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation	-
HyperSeg-S	78.4	HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation	-
PSPNet	-	Pyramid Scene Parsing Network	-
S^2-FPN34	71.0	S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation	-
PIDNet-S (Cityscapes-Pretrained)	80.1	PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers	-
Dilation10	65.3%	Multi-Scale Context Aggregation by Dilated Convolutions	-
S^2-FPN34M	74.2	S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation	-
RTFormer-Slim	81.4	RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer	-
DeepLab	61.6%	Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs	-
BiSeNet	68.7%	BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation	-
DDRNet-23-slim	74.7	Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes	-
ICNet	67.1%	ICNet for Real-Time Semantic Segmentation on High-Resolution Images	-
PP-LiteSeg-T	73.3	PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model	-
SegNet	46.4%	SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation	-

0 of 28 row(s) selected.