Convolution of Convolution: Let Kernels Spatially Collaborate

Abstract

In the biological visual pathway especially the retina, neurons are tiled along spatial dimensions with the electrical coupling as their local association, while in a convolution layer, kernels are placed along the channel dimension singly. We propose convolution of convolution, associating kernels in a layer and letting them collaborate spatially. With this method, a layer can provide feature maps with extra transformations and learn its kernels together instead of isolatedly. It is only used during training, bringing in negligible extra costs; then it can be re-parameterized to common convolution before testing, boosting performance gratuitously in tasks like classification, detection and segmentation. Our method works even better when larger receptive fields are demanded. The code is available on site: https://github.com/Genera1Z/ConvolutionOfConvolution.