A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the part of the input it is on, then summing the results into an output.

Intuitively, a convolution allows for weight sharing - reducing the number of effective parameters - and image translation (allowing for the same feature to be detected in different parts of the input space).

Image Source:


Paper Code Results Date Stars


Task Papers Share
Semantic Segmentation 53 7.45%
Object Detection 45 6.33%
Image Segmentation 29 4.08%
Image Classification 23 3.23%
Medical Image Segmentation 20 2.81%
Denoising 18 2.53%
Classification 16 2.25%
Image Generation 15 2.11%
Super-Resolution 13 1.83%


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