2022-11-28-rostami22a.md

title	abstract	video	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Increasing Model Generalizability for Unsupervised Visual Domain Adaptation	A dominant approach for addressing unsupervised domain adaptation is to map data points for the source and the target domains into an embedding space which is modeled as the output-space of a shared deep encoder. The encoder is trained to make the embedding space domain-agnostic to make a source-trained classifier generalizable on the target domain. A secondary mechanism to improve UDA performance further is to make the source domain distribution more compact to improve model generalizability. We demonstrate that increasing the interclass margins in the embedding space can help to develop a UDA algorithm with improved performance. We estimate the internally learned multi-modal distribution for the source domain, learned as a result of pretraining, and use it to increase the interclass class separation in the source domain to reduce the effect of domain shift. We demonstrate that using our approach leads to improved model generalizability on four standard benchmark UDA image classification datasets and compares favorably against exiting methods.	https://youtu.be/SjxNFO8rK0k	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	rostami22a	0	Increasing Model Generalizability for Unsupervised Visual Domain Adaptation	281	293	281-293	281	false	Rostami, Mohammad	given family Mohammad Rostami	2022-11-28		Proceedings of The 1st Conference on Lifelong Learning Agents	199	inproceedings	date-parts 2022 11 28	https://proceedings.mlr.press/v199/rostami22a/rostami22a.pdf