search

XiaLiPKU / EMANet

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)
https://xialipku.github.io/publication/expectation-maximization-attention-networks-for-semantic-segmentation/
GNU General Public License v3.0
680 stars 131 forks source link

EMA Normalization #1

Closed eugenelawrence closed 5 years ago

eugenelawrence commented 5 years ago

In 6.2.1, it says that 'From the right part of Fig. 3, it is clear to see that LN is better than no normalization'. But in the right part of Fig. 3, it seems that no normalization is better than LN. Is the figure wrong? image

XiaLiPKU commented 5 years ago

This was really a mistake, as I meant to "no better than". I will fix it. Thank you very much！