% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Schuhmann:905696,
author = {Schuhmann, Christoph and Vencu, Richard and Beaumont,
Romain and Kaczmarczyk, Robert and Mullis, Clayton and
Katta, Aarush and Coombes, Theo and Jitsev, Jenia and
Komatsuzaki, Aran},
title = {{LAION}-400{M}: {O}pen {D}ataset of {CLIP}-{F}iltered 400
{M}illion {I}mage-{T}ext {P}airs},
reportid = {FZJ-2022-00923},
pages = {5 p.},
year = {2021},
abstract = {Multi-modal language-vision models trained on hundreds of
millions of image-textpairs (e.g. CLIP, DALL-E) gained a
recent surge, showing remarkable capability toperform zero-
or few-shot learning and transfer even in absence of
per-sample labelson target image data. Despite this trend,
to date there has been no publicly availabledatasets of
sufficient scale for training such models from scratch. To
address thisissue, in a community effort we build and
release for public LAION-400M, adataset with CLIP-filtered
400 million image-text pairs, their CLIP embeddingsand kNN
indices that allow efficient similarity search},
month = {Dec},
date = {2021-12-14},
organization = {NeurIPS Workshop Datacentric AI,
online (online), 14 Dec 2021 - 14 Dec
2021},
cin = {JSC},
cid = {I:(DE-Juel1)JSC-20090406},
pnm = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
and Research Groups (POF4-511)},
pid = {G:(DE-HGF)POF4-5112},
typ = {PUB:(DE-HGF)8},
url = {https://juser.fz-juelich.de/record/905696},
}