A Cookbook of Self-Supervised Learning

Simple item page
dc.contributor.authorBalestriero, Randall
dc.contributor.authorIbrahim, Mark
dc.contributor.authorSobal, Vlad
dc.contributor.authorMorcos, Ari
dc.contributor.authorShekhar, Shashank
dc.contributor.authorGoldstein, Tom
dc.contributor.authorBordes, Florian
dc.contributor.authorBardes, Adrien
dc.contributor.authorMialon, Gregoire
dc.contributor.authorTian, Yuandong
dc.contributor.authorSchwarzschild, Avi
dc.contributor.authorWilson, Andrew Gordon
dc.contributor.authorGeiping, Jonas
dc.contributor.authorGarrido, Quentin
dc.contributor.authorFernandez, Pierre
dc.contributor.authorBar, Amir
dc.contributor.authorPirsiavash, Hamed
dc.contributor.authorLeCun, Yann
dc.contributor.authorGoldblum, Micah
dc.date.accessioned2023-11-09T19:15:22Z
dc.date.available2023-11-09T19:15:22Z
dc.date.issued2023-06-28
dc.description.abstractSelf-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-parameters. Our goal is to lower the barrier to entry into SSL research by laying the foundations and latest SSL recipes in the style of a cookbook. We hope to empower the curious researcher to navigate the terrain of methods, understand the role of the various knobs, and gain the know-how required to explore how delicious SSL can be.en_US
dc.description.urihttps://arxiv.org/abs/2304.12210en_US
dc.format.extent71 pagesen_US
dc.genrejournal articlesen_US
dc.genrepreprintsen_US
dc.identifierdoi:10.13016/m2wqeu-njze
dc.identifier.urihttps://doi.org/10.48550/arXiv.2304.12210
dc.identifier.urihttp://hdl.handle.net/11603/30640
dc.language.isoen_USen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.en_US
dc.titleA Cookbook of Self-Supervised Learningen_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2304.12210.pdf
Size:
1.34 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection