Skip to content

Real-time Domain Adapation in Semantic Segmentation project

Notifications You must be signed in to change notification settings

lucabnf/realtime-DA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-time domain adaptation in semantic segmentation project

This project addresses the semantic segmentation task in a real-time autonomous driving scenario, dealing with domain adaptation between two different datasets. In particular, training our segmentation model on a huge synthetic dataset, we try to improve its performance on a real-world dataset, exploting an unsupervised adversarial training strategy. In this context, three different discriminator solutions are proposed, along with different optimization and regularization techniques, to both improve performance and reduce training and inference time.

Datasets

Download (real-world) CamVid dataset from Google Drive

Download (synthetic) IDDA dataset from Google Drive

Train

1) segmentation train (BiSeNet)

python seg_train.py

2) adversarial train for unsupervised domain adaptation (IDDA+CamVid)

python adv_train.py

Test

python eval.py

Paper

realtime-DA.pdf

Releases

No releases published

Packages

No packages published

Languages