1x1 Convolution

2000년 도입 · 논문 5,641편에서 사용

A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction, efficient low dimensional embeddings, and applying non-linearity after convolutions. It maps an input pixel with all its channels to an output pixel which can be squeezed to a desired output depth. It can be viewed as an MLP looking at a particular pixel location. Image Credit: http://deeplearning.ai

출처: Network In Network

소개 논문: Network In Network