HyperAI超神经

Real Time Semantic Segmentation On Camvid

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

模型名称
mIoU
Paper TitleRepository
EDANet66.4Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
PP-LiteSeg-B75PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
BiSeNet V272.4BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
BiSeNet V2-Large(Cityscapes-Pretrained)78.5BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
BiSeNet V2-Large73.2BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
TD4-PSP1872.6Temporally Distributed Networks for Fast Video Semantic Segmentation
BiSeNet V2(Cityscapes-Pretrained)76.7BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
HyperSeg-S78.4HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation
PSPNet-Pyramid Scene Parsing Network
S^2-FPN3471.0S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation
PIDNet-S (Cityscapes-Pretrained)80.1PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
Dilation1065.3%Multi-Scale Context Aggregation by Dilated Convolutions
S^2-FPN34M74.2S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation
RTFormer-Slim81.4RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
DeepLab61.6%Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
BiSeNet68.7%BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
DDRNet-23-slim74.7Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
ICNet67.1%ICNet for Real-Time Semantic Segmentation on High-Resolution Images
PP-LiteSeg-T73.3PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
SegNet46.4%SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
0 of 28 row(s) selected.