D
Dhruba Ghosh
Publications - 3
Citations - 23
Dhruba Ghosh is an academic researcher. The author has contributed to research in topics: Computer science. The author has an hindex of 2, co-authored 2 publications receiving 5 citations.
Papers
More filters
Journal ArticleDOI
DataComp: In search of the next generation of multimodal datasets
Samir Yitzhak Gadre,Gabriel Ilharco,Alex Fang,Jonathan Hayase,Georgios Smyrnis,T. Nguyen,Ryan Marten,Mitchell Wortsman,Dhruba Ghosh,Jieyu Zhang,Rahim Entezari,Giannis Daras,Sarah I. Pratt,Vivek Ramanujan,Yonatan Bitton,Kalyani Marathe,Stephen Mussmann,Richard Vencu,Mehdi Cherti,Ranjay Krishna,Pang Wei Koh,Olga Saukh,Alexander Ratner,Shuran Song,Hannaneh Hajishirzi,A. Farhadi,Romain Beaumont,Sewoong Oh,Alexandros G. Dimakis,Jenia Jitsev,Yair Carmon,Vaishaal Shankar,Ludwig Schmidt +32 more
TL;DR: DataComp as mentioned in this paper is a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl, which can be used to design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing the resulting model on 38 downstream test sets.
Proceedings ArticleDOI
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level
TL;DR: The authors found that BERT-Large is worse than BERT Mini on at least 1-4% of instances across MNLI, SST-2, and QQP, compared to the overall accuracy improvement of 2-10%.
Posted Content
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level
TL;DR: The authors found that BERT-Large is worse than BERT Mini on at least 1-4% of instances across MNLI, SST-2, and QQP, compared to the overall accuracy improvement of 2-10%.