Загрузка...

Generative-Discriminative Complementary Learning

The majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of...

Полное описание

Сохранить в:
Библиографические подробности
Опубликовано в: :Proc AAAI Conf Artif Intell
Главные авторы: Xu, Yanwu, Gong, Mingming, Chen, Junxiang, Liu, Tongliang, Zhang, Kun, Batmanghelich, Kayhan
Формат: Artigo
Язык:Inglês
Опубликовано: 2020
Предметы:
Online-ссылка:https://ncbi.nlm.nih.gov/pmc/articles/PMC7494202/
https://ncbi.nlm.nih.gov/pubmed/32944410
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1609/aaai.v34i04.6126
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!