ICCV：Why Approximate Matrix Square Root Outperforms Accurate SVD in Global ...

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

Why Approximate Matrix Square Root Outperforms Accurate SVD in Global
             Covariance Pooling?

                     Yue Song, Nicu Sebe, and Wei Wang
                    DISI, University of Trento, Trento, Italy
                   {yue.song nicu.sebe wei.wang}@unitn.it


            Abstract
  Global Covariance Pooling (GCP) aims at exploiting
the second-order statistics of the convolutional feature. Its
effectiveness has been demonstrated in boosting the clas-
sification performance of ...

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：OUTPERFORMS Approximate Outperform accurate Perform