HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

Real Time Semantic Segmentation On Cityscapes

評価指標

Frame (fps)
mIoU

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper Title
PIDNet-L31.1(3090)80.6%PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
SFNet-R1825.7(1080Ti)80.4%Semantic Flow for Fast and Accurate Scene Parsing
PIDNet-M42.2(3090)79.8%PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
PIDNet-S93.2(3090)78.6%PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
RegSeg (no ImageNet pretraining)3078.3%Rethinking Dilated Convolution for Real-time Semantic Segmentation
PP-LiteSeg-B2102.6(1080Ti)77.5%PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
DDRNet-23-slim101.6(2080Ti)77.4%Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
STDC2-7597.0(1080Ti)76.8%Rethinking BiSeNet For Real-time Semantic Segmentation
SwinMTL-76.41%SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images
HyperSeg-M36.975.8%HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation
SwiftNetRN-1839.975.5%In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images
BiSeNet V2-Large47.375.3%BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
STDC1-75126.775.3%Rethinking BiSeNet For Real-time Semantic Segmentation
TD4-BISE1847.6 (Titan X)74.9%Temporally Distributed Networks for Fast Video Semantic Segmentation
PP-LiteSeg-T2143.6(1080Ti)74.9%PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
ShelfNet1859.274.8%ShelfNet for Fast Semantic Segmentation
BiSeNet(ResNet-18)65.574.7%BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
BiSeNet65.574.7%BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
PP-LiteSeg-B1195.3(1080Ti)73.9%PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
SegBlocks-RN18 (t=0.4)48.6 (1080Ti)73.8%SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation
0 of 39 row(s) selected.
Real Time Semantic Segmentation On Cityscapes | SOTA | HyperAI超神経