Convolutions

Convolution

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: https://arxiv.org/pdf/1603.07285.pdf

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Semantic Segmentation 46 6.34%
Object Detection 41 5.66%
Image Generation 26 3.59%
Image Classification 24 3.31%
Image Segmentation 23 3.17%
Denoising 18 2.48%
Classification 14 1.93%
Super-Resolution 13 1.79%
Self-Supervised Learning 11 1.52%

Components


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

Categories