1x1 Convolutional Layer

A 1x1 Convolutional Layer is a convolutional layer with a 1x1 convolution kernel.

• Context:
  • It can shrink the number of channels.
  • …
• Counter-Example(s):
  • 3x3 Convolutional Layer.
• See: ConvNet, Inception Network.

---

---

References

2018

• https://www.quora.com/What-does-a-1x1-convolutional-layer-do
  • QUOTE: A 1x1 convolution matrix essentially squashes the depth dimension of an input volume (W x H x D) leaving its width and height intact (W x H x 1). An n x n convolution matrix, in comparison, not only squashes the depth dimension of an input volume - it could, based on its dimensions, input volume dimensions and pad values, alter the width and height of the input volume too.

2017

• Andrew Ng. (2016). “Neural Networks - Networks in Networks and 1x1 Convolutions.” YouTube Lecture.
  • …

2013

• (Lin et al., 2013) ⇒ Min Lin, Qiang Chen, and Shuicheng Yan. (2013). “Network in Network.” arXiv preprint arXiv:1312.4400
  • QUOTE: ... The cross channel parametric pooling layer is also equivalent to a convolution layer with 1x1 convolution kernel. ...
  • QUOTE: https://openreview.net/forum?id=ylE6yojDR5yqX&noteId=ylE6yojDR5yqX

---