DomainLab: A modular Python package for domain generalization in deep learning

arXiv:2403.14356v1 Announce Type: new
Abstract: Poor generalization performance caused by distribution shifts in unseen domains often hinders the trustworthy deployment of deep neural networks. Many domain generalization techniques address this problem by adding a domain invariant regularization loss terms during training. However, there is a lack of modular software that allows users to combine the advantages of different methods with minimal effort for reproducibility. DomainLab is a modular Python package for training user specified neural networks with composable regularization loss …

arxiv cs.lg cs.se deep learning domain modular package python type