Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Jiang, Ruijie"'
For a widely-studied data model and general loss and sample-hardening functions we prove that the losses of Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised Contrastive Learning (UCL) are minimized by representations that exhi
Externí odkaz:
http://arxiv.org/abs/2311.05139
In typical medical image classification problems, labeled data is scarce while unlabeled data is more available. Semi-supervised learning and self-supervised learning are two different research directions that can improve accuracy by learning from ex
Externí odkaz:
http://arxiv.org/abs/2307.08919
Through minimization of an appropriate loss function such as the InfoNCE loss, contrastive learning (CL) learns a useful representation function by pulling positive samples close to each other while pushing negative samples far apart in the embedding
Externí odkaz:
http://arxiv.org/abs/2209.00078
This paper considers the problem of measure estimation under the barycentric coding model (BCM), in which an unknown measure is assumed to belong to the set of Wasserstein-2 barycenters of a finite set of known measures. Estimating a measure under th
Externí odkaz:
http://arxiv.org/abs/2201.12195
We study the problem of designing hard negative sampling distributions for unsupervised contrastive representation learning. We propose and analyze a novel min-max framework that seeks a representation which minimizes the maximum (worst-case) general
Externí odkaz:
http://arxiv.org/abs/2111.03169
This paper shows that a popular approach to the supervised embedding of documents for classification, namely, contrastive Word Mover's Embedding, can be significantly enhanced by adding interpretability. This interpretability is achieved by incorpora
Externí odkaz:
http://arxiv.org/abs/2111.01023
Qualitative analysis of verbal data is of central importance in the learning sciences. It is labor-intensive and time-consuming, however, which limits the amount of data researchers can include in studies. This work is a step towards building a stati
Externí odkaz:
http://arxiv.org/abs/2011.13384
Autor:
Jiang, Ruijie1,2 (AUTHOR) jiang6494@alu.cau.edu.cn, Zhang, Xinyi1 (AUTHOR) sy20213050936@cau.edu.cn, Xia, Maohua2 (AUTHOR) zhaosufen111@126.com, Zhao, Sufen2 (AUTHOR) wangyunshengabc@163.com, Wang, Yunsheng2 (AUTHOR) putianchun0628@sina.com, Pu, Tianchun2 (AUTHOR) zhang_chenglin01@sina.com, Zhang, Chenglin2 (AUTHOR) jrj20632312@163.com, Wu, Zhong2 (AUTHOR) 13911619616@163.com, Xu, Haihong2 (AUTHOR), Fan, Kai1 (AUTHOR) fan@cau.edu.cn
Publikováno v:
Animals (2076-2615). Oct2023, Vol. 13 Issue 19, p3023. 13p.
Publikováno v:
Psychonomic Bulletin & Review; Aug2024, Vol. 31 Issue 4, p1856-1866, 11p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.