Differentiable Data Augmentation with Kornia
Paper · https://arxiv.org/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 approaches that make use of Kornia DDA.
First seen by Oriel on .
AI summary
This paper reviews Kornia’s differentiable data augmentation module for 2D and 3D tensors, its PyTorch integration, benchmarks, and applications.
- Kornia DDA provides differentiable augmentation pipelines for both spatial 2D and volumetric 3D tensors.
- The module integrates with PyTorch components including autograd for differentiability and optim for optimization.
- The paper benchmarks Kornia DDA against different data augmentation frameworks.
- It also reviews approaches that use Kornia DDA for differentiable data augmentation strategies.
#kornia #data augmentation #pytorch #computer vision
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Points
Score reported by the source.
- Hugging Face Papers: 1, latest observation ; 0 over observed period since
Comments
Comment count reported by the source.
- Hugging Face Papers: 0, latest observation ; 0 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| Hugging Face Papers | 2011.09832 | https://arxiv.org/abs/2011.09832 Read discussion |