Bi-linearly weighted fractional max pooling
作者: Siang Thye HangMasaki Aono
作者单位: 1Toyohashi University of Technology
刊名: Multimedia Tools and Applications, 2017, Vol.76 (21), pp.22095-22117
来源数据库: Springer Nature Journal
DOI: 10.1007/s11042-017-4840-5
关键词: Fractional max poolingConvolutional neural networkDeep learning
原始语种摘要: In this paper, we propose to extend the flexibility of the commonly used 2 × 2 non-overlapping max pooling for Convolutional Neural Network. We name it as Bi-linearly Weighted Fractional Max-Pooling. This proposed method enables max pooling operation below stride size 2, and is computed based on four bi-linearly weighted neighboring input activations. Currently, in a 2 × 2 non-overlapping max pooling operation, as spatial size is halved in both x and y directions, three-quarter of activations in the feature maps are discarded. As such reduction is too abrupt, amount of said pooling operation within a Convolutional Neural Network is very limited: further increasing the number of pooling operation results in too little activation left for subsequent operations. Using our proposed pooling...
全文获取路径: Springer Nature  (合作)
影响因子:1.014 (2012)

  • pooling 并批
  • flexibility 柔顺性
  • operation 运算
  • linearly 成直线地
  • proposed 建议的
  • usage 使用率
  • weighted 加权
  • learning 学识
  • layered 成层的
  • reduction 减少