Publication

Differentiable data augmentation with Kornia

Conference Article

Conference

Workshop on Differentiable Vision, Graphics, and Physics Applied to Machine Learning (DiffCVGP)

Edition

1st

Doc link

https://montrealrobotics.ca/diffcvgp/assets/papers/8.pdf

File

Download the digital copy of the doc pdf document

Authors

Abstract

In this paper we present a review of the Kornia differentiable data augmentation (DDA) module for both for spatial (2D) and volumetric (3D) tensors. This module leverages differentiable computer vision solutions from Kornia, with an aim of integrating data augmentation (DA) pipelines and strategies to existing PyTorch components (e.g. autograd for differentiability, optim for optimization). In addition, we provide a benchmark comparing different DA frameworks and a short review for a number of approaches that make use of Kornia DDA.

Categories

computer vision.

Author keywords

computer visio, differentiable data augmentation, deep learning

Scientific reference

J. Shi, E. Riba, D. Mishkin, F. Moreno-Noguer and A. Nicolaou. Differentiable data augmentation with Kornia, 1st Workshop on Differentiable Vision, Graphics, and Physics Applied to Machine Learning, 2020, Online.