Active Convolution

Introduced by Jeon et al. in Active Convolution: Learning the Shape of Convolution for Image Classification

An Active Convolution is a type of convolution which does not have a fixed shape of the receptive field, and can be used to take more diverse forms of receptive fields for convolutions. Its shape can be learned through backpropagation during training. It can be seen as a generalization of convolution; it can define not only all conventional convolutions, but also convolutions with fractional pixel coordinates. We can freely change the shape of the convolution, which provides greater freedom to form CNN structures. Second, the shape of the convolution is learned while training and there is no need to tune it by hand

Source: Active Convolution: Learning the Shape of Convolution for Image Classification

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Classification	1	33.33%
General Classification	1	33.33%
Image Classification	1	33.33%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Convolutions