• <blockquote id="o6wqy"></blockquote>
  • <samp id="o6wqy"></samp>
  • <samp id="o6wqy"><label id="o6wqy"></label></samp>
  • <blockquote id="o6wqy"></blockquote>
  • <blockquote id="o6wqy"></blockquote>
    <samp id="o6wqy"><samp id="o6wqy"></samp></samp>
  • <samp id="o6wqy"></samp>
  • <samp id="o6wqy"><sup id="o6wqy"></sup></samp>
  • <samp id="o6wqy"><sup id="o6wqy"></sup></samp>
  • PDO-eConvs: Partial Differential Operator Based

    來源:科學技術處、電子與通信工程系發布時間:2020-07-24

    【講座題目】PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions

    【講座時間】2020年7月28日(星期二)上午8:35

    【講座地點】網絡直播:https://live.bilibili.com/22339632

    【主 人】林宙辰,北京大學教授

    【主講人簡介】

    北京大學教授,IAPR/IEEE Fellow,國家杰青,中國圖象圖形學學會機器視覺專委會主任,中國自動化學會模式識別與機器智能專委會副主任。研究領域為計算機視覺、機器學習、圖像處理、模式識別和數值優化。發表論文200余篇,英文專著2本。任 CVPR 2014/2016/2019/2020/2021 、 ICCV 2015 、 NIPS 2015/2018/2019/2020、ICML 2020、IJCAI 2020/2021、AAAI 2019/2020 和 ICLR 2021 領域主席,IEEE T. PAMI、IJCV 編委。

    【內容簡介】

    Recent research has shown that incorporating equivariance into neural network architectures is very helpful, and there have been some works investigating the equivariance of networks under group actions. However, as digital images and feature maps are on the discrete meshgrid, corresponding equivariance-preserving transformation groups are very limited. We deal with this issue from the connection between convolutions and partial differential operators (PDOs). In theory, assuming inputs to be smooth, we transform PDOs and propose a system which is equivariant to a much more general continuous group, the n-dimension Euclidean group. In implementation, we discretize the system using the numerical schemes of PDOs, deriving approximately equivariant convolutions (PDO-eConvs). Theoretically, the approximation error of PDO-eConvs is of the quadratic order. It is the first time that the error analysis is provided when the equivariance is approximate. Extensive experiments on rotated MNIST and natural image classification show that PDO-eConvs perform competitively yet use parameters much more efficiently. Particularly, compared with Wide ResNets, our methods result in better results using only 12.6% parameters.

     

    返回
    反波胆足球分析网

    反波胆

    足球反波胆 天方体育反波胆 tg反波胆怎样套利 淘金反波胆技巧 tg淘金反波胆哪里注册 足球反波胆平台有几个 反波胆理财 反波胆如何下最稳 反波胆分析技巧 反波胆有哪些靠谱平台 足球反波胆理财 反波胆TG 反波胆平台哪个最可靠 今天足球反波胆比分推荐 ifa反波胆制度 吉运宝盈反波胆 反波胆是什么意思 反波胆足球 反波胆比分和获利百分比 富达体育反波胆 ifa足球反波胆 淘金反波胆安全吗 反波胆真能赚到钱么 足球比赛反波胆是什么意思 fbd反波胆平台 淘金反波胆平台网址 反波胆怎么买 反波胆有哪些平台 tg淘金反波胆靠谱吗 足球反波胆是什么 反波胆玩法 tg淘金反波胆微信群 tg淘金反波胆哪个比分安全 足球反波胆平台哪个靠谱 反波胆角球 反波胆ifa TG反波胆爆单 tg淘金反波胆怎么盈利 反波胆网站 tg反波胆怎么玩 反波胆TG多久爆弹一次 玩反波胆技巧 bet168 反波胆 反波胆怎么分析 淘金反波胆下载 天行体育反波胆下载 反波胆平台哪个最可靠