2022-06-28-bao22c.md

title	booktitle	abstract	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
Generative Modeling for Multi-task Visual Learning	Proceedings of the 39th International Conference on Machine Learning	Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider a novel problem of learning a shared generative model that is useful across various visual perception tasks. Correspondingly, we propose a general multi-task oriented generative modeling (MGM) framework, by coupling a discriminative multi-task network with a generative network. While it is challenging to synthesize both RGB images and pixel-level annotations in multi-task scenarios, our framework enables us to use synthesized images paired with only weak annotations (i.e., image-level scene labels) to facilitate multiple visual tasks. Experimental evaluation on challenging multi-task benchmarks, including NYUv2 and Taskonomy, demonstrates that our MGM framework improves the performance of all the tasks by large margins, consistently outperforming state-of-the-art multi-task approaches in different sample-size regimes.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bao22c	0	Generative Modeling for Multi-task Visual Learning	1537	1554	1537-1554	1537	false	Bao, Zhipeng and Hebert, Martial and Wang, Yu-Xiong	given family Zhipeng Bao given family Martial Hebert given family Yu-Xiong Wang	2022-06-28		Proceedings of the 39th International Conference on Machine Learning	162	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v162/bao22c/bao22c.pdf