2023-12-02-dasari23a.md

title	section	openreview	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
An Unbiased Look at Datasets for Visuo-Motor Pre-Training	Poster	qVc7NWYTRZ6	Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but out-of-domain data (e.g., videos of egocentric interactions) and then transferring them to target robotics tasks. While the field is heavily focused on developing better pre-training algorithms, we find that dataset choice is just as important to this paradigm’s success. After all, the representation can only learn the structures or priors present in the pre-training dataset. To this end, we flip the focus on algorithms, and instead conduct a dataset centric analysis of robotic pre-training. Our findings call into question some common wisdom in the field. We observe that traditional vision datasets (like ImageNet, Kinetics and 100 Days of Hands) are surprisingly competitive options for visuo-motor representation learning, and that the pre-training dataset’s image distribution matters more than its size. Finally, we show that common simulation benchmarks are not a reliable proxy for real world performance and that simple regularization strategies can dramatically improve real world policy learning.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	dasari23a	0	An Unbiased Look at Datasets for Visuo-Motor Pre-Training	1183	1198	1183-1198	1183	false	Dasari, Sudeep and Srirama, Mohan Kumar and Jain, Unnat and Gupta, Abhinav	given family Sudeep Dasari given family Mohan Kumar Srirama given family Unnat Jain given family Abhinav Gupta	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/dasari23a/dasari23a.pdf