• Corpus ID: 227054123

Differentiable Data Augmentation with Kornia

@article{Shi2020DifferentiableDA,
  title={Differentiable Data Augmentation with Kornia},
  author={Jian Shi and Edgar Riba and Dmytro Mishkin and Francesc Moreno and Anguelos Nicolaou},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.09832}
}
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… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 12 REFERENCES
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
TLDR
Kornia is composed of a set of modules containing operators that can be inserted inside neural networks to train models to perform image transformations, camera calibration, epipolar geometry, and low level image processing techniques, such as filtering and edge detection that operate directly on high dimensional tensor representations.
Differentiable Augmentation for Data-Efficient GAN Training
TLDR
DiffAugment is a simple method that improves the data efficiency of GANs by imposing various types of differentiable augmentations on both real and fake samples, and can generate high-fidelity images using only 100 images without pre-training, while being on par with existing transfer learning algorithms.
Spatial Transformer Networks
TLDR
This work introduces a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within the network, and can be inserted into existing convolutional architectures, giving neural networks the ability to actively spatially transform feature maps.
Albumentations: fast and flexible image augmentations
TLDR
Albumentations is presented, a fast and flexible open source library for image augmentation with many various image transform operations available that is also an easy-to-use wrapper around other augmentation libraries.
Automatic differentiation in PyTorch
TLDR
An automatic differentiation module of PyTorch is described — a library designed to enable rapid research on machine learning models that focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead.
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
TLDR
This paper proposes a differentiable policy search pipeline for data augmentation, which achieves significantly faster searching than prior work without a performance drop and introduces approximate gradients for several transformation operations with discrete parameters.
Meta Approach to Data Augmentation Optimization
TLDR
This paper proposes to optimize image recognition models and data augmentation policies simultaneously to improve the performance using gradient descent, and achieves efficient and scalable training by approximating the gradient of policies by implicit gradient with Neumann series approximation.
Repeatability Is Not Enough: Learning Affine Regions via Discriminability
TLDR
It is shown that maximizing geometric repeatability does not lead to local regions, a.k.a features, that are reliably matched and this necessitates descriptor-based learning, and a novel hard negative-constant loss function is proposed for learning of affine regions.
The OpenCV Library
  • Dr. Dobb’s Journal of Software Tools,
  • 2000
Deep Learning
...
1
2
...