Skip to main content
Artificial Intelligence

Return to Question

Bumped by Community user
Bumped by Community user
added 32 characters in body; edited tags; edited title
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 114
  • 205

What is the point of using 1D and 2D convolutions ofwith a kernel size of 1, or and 1x1, etc respectively?

I understand the gist of what convolutional neural networks do and what they are used for, but I still wrestle a bit with how they function on a conceptual level. For example, I get that filters with kernel size >1greater than 1 are used as feature detectors, and that number of filters =is equal to the number of output channels for a convolutional layer, and the number of features being detected scales with the number of filters/channels.

However, as of recently, I've been encountering an increasing number of models that employ 1- or 2-D2D convolutions with kernel sizes of 1 or 1x1, and I can't quite grasp why. It feels to me like they defeat the purpose of performing a convolution in the first place. 

What is the advantage of using such layers? Are they not just equivalent to multiplying each channel by a trainable, scalar value?

What is the point of using convolutions of kernel size 1, or 1x1, etc?

I understand the gist of what convolutional networks do and what they are used for, but I still wrestle a bit with how they function on a conceptual level. For example, I get that filters with kernel size >1 are used as feature detectors, and that number of filters = number of output channels for a convolutional layer and the number of features being detected scales with the number of filters/channels.

However, as of recently I've been encountering an increasing number of models that employ 1- or 2-D convolutions with kernel sizes of 1 or 1x1, and I can't quite grasp why. It feels to me like they defeat the purpose of performing a convolution in the first place. What is the advantage of using such layers? Are they not just equivalent to multiplying each channel by a trainable, scalar value?

What is the point of using 1D and 2D convolutions with a kernel size of 1 and 1x1 respectively?

I understand the gist of what convolutional neural networks do and what they are used for, but I still wrestle a bit with how they function on a conceptual level. For example, I get that filters with kernel size greater than 1 are used as feature detectors, and that number of filters is equal to the number of output channels for a convolutional layer, and the number of features being detected scales with the number of filters/channels.

However, recently, I've been encountering an increasing number of models that employ 1- or 2D convolutions with kernel sizes of 1 or 1x1, and I can't quite grasp why. It feels to me like they defeat the purpose of performing a convolution in the first place. 

What is the advantage of using such layers? Are they not just equivalent to multiplying each channel by a trainable, scalar value?

Source Link
Arcturai
Arcturai
  • 81
  • 1

What is the point of using convolutions of kernel size 1, or 1x1, etc?

I understand the gist of what convolutional networks do and what they are used for, but I still wrestle a bit with how they function on a conceptual level. For example, I get that filters with kernel size >1 are used as feature detectors, and that number of filters = number of output channels for a convolutional layer and the number of features being detected scales with the number of filters/channels.

However, as of recently I've been encountering an increasing number of models that employ 1- or 2-D convolutions with kernel sizes of 1 or 1x1, and I can't quite grasp why. It feels to me like they defeat the purpose of performing a convolution in the first place. What is the advantage of using such layers? Are they not just equivalent to multiplying each channel by a trainable, scalar value?