ICML-Generating images with sparse representations

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Generating images with sparse representations

             Charlie Nash 1 Jacob Menick 1 Sander Dieleman 1 Peter Battaglia 1

            Abstract
   The high dimensionality of images presents ar-
   chitecture and sampling-efficiency challenges for
   likelihood-based generative models. Previous ap-
   proaches such as VQ-VAE use deep autoencoders
   to obtain compact representations, which are more
   practical as inputs for likelihood-based models.
   We present an alternative approach, insp ...

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Presentation Presentatio generating represent Present