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

最新推荐文章于 2024-04-16 10:14:36 发布

chn13

最新推荐文章于 2024-04-16 10:14:36 发布

阅读量2.5k

点赞数 3

分类专栏： paper-note 文章标签：深度学习 CNN

本文链接：https://blog.csdn.net/chn13/article/details/53609791

版权

20 篇文章 2 订阅

订阅专栏

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.
An extreme version of this separation is to entirely decouple the cross-channel and spatial operations, naming Xception.

Xception module:
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

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.