Back to Search Start Over

Differentiable data augmentation with Kornia

Authors :
Institut de Robòtica i Informàtica Industrial
Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI
Shi, Jian
Riba Pi, Edgar
Mishkin, Dmytro
Moreno-Noguer, Francesc
Nicolaou, Anguelos
Institut de Robòtica i Informàtica Industrial
Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI
Shi, Jian
Riba Pi, Edgar
Mishkin, Dmytro
Moreno-Noguer, Francesc
Nicolaou, Anguelos
Publication Year :
2020

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.<br />Postprint (author's final draft)

Details

Database :
OAIster
Notes :
5 p., application/pdf, English
Publication Type :
Electronic Resource
Accession number :
edsoai.on1247077625
Document Type :
Electronic Resource