[Paper note] Xception: Deep Learning with Depthwise Separable Convolutions

Intuition

  • Inception series
  • Conv maps cross-channel correlation and spatial correlation at the same time.
  • Inception module makes this process easier and more efficient by explicitly factoring it into a series of operations that would independently look at cross-channel correlations and at spatial correlations.
  • 1x1 Conv -> cross-channel correlation; 3x3 & 5x5 Conv -> spatial correlation.
    Inception
  • An extreme version of this separation is to entirely decouple the cross-channel and spatial operations, naming Xception.

Xception

  • Xception module:
    Xception
  • First use 1x1 Conv
  • Conduct depthwise separable convolution (DSC): each feature-map have different 3x3 Conv, then concatenate the result of each Conv.
  • Advantages: Efficient parameter usage
  • Whole model
    Model

Experiment

  • Dataset: JET (internal Google dataset), ImageNet, FastEval14k.
  • Result
    • Xception converges faster than Inception V3 and gets higher accuracy.
    • 21.0% top-1, 5.5% top-5 error on ImageNet.
    • Better with residual connection.
    • Worse with non-linear in between the 1x1 and DSC.
  • 3
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值