[IPOL announce] new article: A Study of RobustNet, a Domain Generalization Method for Semantic Segmentation

[announcements about the IPOL journal]

A new article is available in IPOL: http://www.ipol.im/pub/art/2022/433/

Xavier Bou,
A Study of RobustNet, a Domain Generalization Method for Semantic 
Segmentation,
Image Processing On Line, 12 (2022), pp. 469–479.
https://doi.org/10.5201/ipol.2022.433

Abstract
Domain Generalization alleviates the domain gap between training set and 
test set, improving the performance of deep neural networks on 
out-of-dataset data. This opens the possibility of deploying models on 
unlabelled data that were previously pretrained on other datasets. In 
this article, we study the ideas and performance of RobustNet [Choi et 
al. CVPR 2021], a recent method for Domain Generalization in Urban-Scene 
Semantic Segmentation. Instead of exposing the network to a wide range 
of domains, RobustNet tries to separate domain-variant from 
domain-invariant features via a whitening transformation. Then, only the 
domain invariant features are used for training, which allows to reduce 
training time since no combination of datasets is needed to achieve 
domain invariance. In addition, we provide an easy-to-use demo where 
users can quickly test their own data and compare the results of 
RobustNet against the state of the art for semantic segmentation.