Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

License

NotificationsYou must be signed in to change notification settings

linksense/LightNetPlusPlus

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This repository contains the code (PyTorch-1.0+,W.I.P.) for: "LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation" by Huijun Liu.
LightNet++ is an advanced version ofLightNet, which purpose to get more concise model design,smaller models, and better performance.

  • MobileNetV2Plus: Modified MobileNetV2 (backbone)[1,8] + DSASPPInPlaceABNBlock[2,3] +Parallel Bottleneck Channel-Spatial Attention Block (PBCSABlock)[6] + UnSharp Masking (USM) + Encoder-Decoder Arch.[3] +InplaceABN[4].

  • ShuffleNetV2Plus: Modified ShuffleNetV2 (backbone)[1,8] + DSASPPInPlaceABNBlock[2,3] +Parallel Bottleneck Channel-Spatial Attention Block (PBCSABlock)[6]+ UnSharp Masking (USM) + Encoder-Decoder Arch.[3] +InplaceABN[4].

  • MixSeg-MixBiFPN: Modified MixNet (backbone)[1,8] + MixBiFPNBlock[2,3] + Encoder-Decoder Arch.[3]

More aboutUSM(Unsharp Mask)-Operator Block see Repo:SharpPeleeNet

Dependencies

Datasets for Autonomous Driving

Results

Results on Cityscapes (Pixel-level/Semantic Segmentation)

ModelmIoU (S.S* Mixed Precision)Model Weight
MobileNetV2Plus X1.071.5314 (WIP)cityscapes_mobilenetv2plus_x1.0.pkl (14.3 MB)
ShuffleNetV2Plus X1.069.0885-72.5255 (WIP)cityscapes_shufflenetv2plus_x1.0.pkl (8.59 MB)
MixSeg+MixBiFPN ArchS72.2321 (WIP)cityscapes_mixseg_archs_mixbifpn.pkl (16.4 MB)
  • S.S.: Single Scale (1024x2048)

Feature Visualization


[8]ページ先頭

©2009-2025 Movatter.jp