Viet-Anh on Software Logo

What is: CondConv?

SourceCondConv: Conditionally Parameterized Convolutions for Efficient Inference
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

CondConv, or Conditionally Parameterized Convolutions, are a type of convolution which learn specialized convolutional kernels for each example. In particular, we parameterize the convolutional kernels in a CondConv layer as a linear combination of nn experts (α1W1++αnWn)x(\alpha_1 W_1 + \ldots + \alpha_n W_n) * x, where α1,,αn\alpha_1, \ldots, \alpha_n are functions of the input learned through gradient descent. To efficiently increase the capacity of a CondConv layer, developers can increase the number of experts. This can be more computationally efficient than increasing the size of the convolutional kernel itself, because the convolutional kernel is applied at many different positions within the input, while the experts are combined only once per input.