- Why MobileNet and Its Variants (e.g. ShuffleNet) Are Fast文章通過輸入與輸出連通性的角度直觀上分析了不同卷積模式計算量的改變情況。
基礎卷積模塊
- standard convolution
標準卷積的計算量爲HWNK²M,可以分爲3部分
(1) the spatial size of the input feature map HxW,
(2) the size of convolution kernel K²
(3) the numbers of input and output channels NxM.
- group convolution
-
Depthwise Convolution
- Pointwise Convolution
- Depthwise separable convolution
- channel Shuffle
卷積操作變體
- Resnet
Residual blocks — Building blocks of ResNet文章較詳細的介紹了skip connection及殘差網絡名稱的由來。
Let us consider a neural network block, whose input is x and we would like to learn the true distribution H(x). Let us denote the difference (or the residual) between this as
R(x) = Output — Input = H(x) — x
Rearranging it, we get,
H(x) = R(x) + x
Our residual block is overall trying to learn the true output, H(x) and if you look closely at the image above, you will realize that since we have an identity connection coming due to x, the layers are actually trying to learn the residual, R(x). So to summarize, the layers in a traditional network are learning the true output (H(x))whereas the layers in a residual network are learning the residual (R(x)). Hence, the name: Residual Block
-
ResNeXt
該網絡結構與inception及group convolution的視圖如下。
-
Squeeze-and-Excitation (SE) Block
參考文獻: