리미

https://arxiv.org/abs/1807.03748 Representation Learning with Contrastive Predictive CodingWhile supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose a universal unsuarxiv.org Abstract본 연구에서는 고차원 데이터를 기반으로 유용한 표현을 추출하..

https://arxiv.org/abs/2209.13430 UniCLIP: Unified Framework for Contrastive Language-Image Pre-trainingPre-training vision-language models with contrastive objectives has shown promising results that are both scalable to large uncurated datasets and transferable to many downstream applications. Some following works have targeted to improve data efficiency barxiv.org Abstract최근에 CLIP의 data 부족 문제를..