About the code of ADVENT

valeoai / ADVENT

Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

https://arxiv.org/abs/1811.12833

Other

382 stars 70 forks source link

About the code of ADVENT #6

Closed Solacex closed 5 years ago

Solacex commented 5 years ago

Hello,

I am trying to reproduce the result reported in the paper( ADVENT) but the result I got is 42.36(advent only, best result), I want to know if there is any mistake in the configure or have you ever meet such result?

tuanhungvu commented 5 years ago

Hello @Solacex , as adversarial training is not stable, you may have to train a few times to reach the comparable performance. In our experiments, we observed performance ranging from 43.3-44.1% . Please refer to https://github.com/valeoai/ADVENT#training for more of our experiment details. T-H