Caesar AI Atlas

Depthwise Separable Convolutional Neural Network

Also known as: Depthwise Separable Convolutional Neural Network (sepCNN) Β· sepCNN Β· Depthwise Separable Convolutional Neural Network sepCNN

Caesar AI Atlas Definition

Depthwise separable convolutional neural network (sepCNN) is a convolutional architecture that replaces standard convolutions with more efficient depthwise separable convolutions. These operations separate spatial filtering from channel mixing, reducing computation while preserving useful representation capacity.

Other Definitions

Depthwise Separable Convolutional Neural Network [sepCNN] Source

A convolutional neural network architecture based on Inception, but where Inception modules are replaced with depthwise separable convolutions. Also known as Xception. A depthwise separable convolution (also abbreviated as separable convolution) factors a standard 3D convolution into two separate convolution operations that are more computationally efficient: first, a depthwise convolution, with a depth of 1 (n n 1), and then second, a pointwise convolution, with length and width of 1 (1 1 n). To learn more, see Xception: Deep Learning with Depthwise Separable Convolutions.

Related Terms