A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Differentiable Data Augmentation with Kornia
[article]
2020
arXiv
pre-print
Preserved Fulltext
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 ...
In this paper we present a review of the Kornia differentiable data augmentation (DDA) module for both for spatial (2D) and volumetric (3D) tensors. ...
Discussion We presented Kornia DDA that aligned with PyTorch API design principles with a focus on usability, to perform efficient differentiable augmentation pipelines for both production and research ...
arXiv:2011.09832v1
fatcat:p6wgj4eumrdmhja6dyvnwfmkfu
A survey on Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This work presents Kornia, an open source computer vision library built upon a set of differentiable routines and modules that aims to solve generic computer vision problems. ...
The package uses PyTorch as its main backend, not only for efficiency but also to take advantage of the reverse auto-differentiation engine to define and compute the gradient of complex functions. ...
Example 1: Data augmentation pipeline Example showing how flexible is Kornia to define a data augmentation pipeline using other PyTorch components. ...
arXiv:2009.10521v1
fatcat:wjyp5nzbfzfmjpvuxfaxydh5ra
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. ...
The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. ...
With the rise of deep learning, most of the standard computer vision frameworks have moved to being used more for certain geometric vision functions, data pre-processing, data augmentation on the CPU in ...
arXiv:1910.02190v2
fatcat:shnrjgnvyfbgzaskdjznlb6psu
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
2020
2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This work presents Kornia -an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems. ...
The package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions. ...
, data augmentation on the CPU in order to be transferred later to the GPU as well as post processing to refine results. ...
doi:10.1109/wacv45572.2020.9093363
dblp:conf/wacv/RibaMPRB20
fatcat:dtyl4bijcfee3dv7se3hhgfmpa
Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Kaolin provides efficient implementations of differentiable 3D modules for use in deep learning systems. ...
Kaolin packages together several differentiable graphics modules including rendering, lighting, shading, and view warping. ...
This allows for operator overloading over common functions for data augmentation and modifications supported by the package. ...
arXiv:1911.05063v2
fatcat:2mbh3eqljrfv5ervwrwtcu54ry
Local Patch AutoAugment with Multi-Agent Collaboration
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Data augmentation (DA) plays a critical role in improving the generalization of deep learning models. Recent works on automatically searching for DA policies from data have achieved great success. ...
The agents cooperate with each other to achieve the optimal augmentation effect of the entire image by sharing a team reward. ...
Therefore, we compare the feedback of target network φ(•) on the augmented data processed by our proposed PAA x with the original data x and take their difference on the training losses as the reward for ...
arXiv:2103.11099v2
fatcat:zxbiwct4urepxcmen7uba76iki
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
As the objective of training, we minimize the distance between the distributions of augmented data and the original data, which can be differentiated. ...
In this paper, we propose a differentiable policy search pipeline for data augmentation, which is much faster than previous methods. ...
We transplanted the operations described in section 3.1 to PyTorch [22] , a tensor computation library with automatic differentiation. For geometric operations, we extend functions in kornia [25] . ...
arXiv:1911.06987v1
fatcat:euoxrg2coredvlsbfkqod3wr2i
Self-Distilled Hashing for Deep Image Retrieval
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To mitigate this issue, data augmentation can be applied during training. ...
In this work, we propose a novel self-distilled hashing scheme to minimize the discrepancy while exploiting the potential of augmented data. ...
Instead of including non-differentiable quantization process in model training, we learn H in the real space to estimate optimal b with continuously relaxed h while fully exploiting the power of data augmentation ...
arXiv:2112.08816v1
fatcat:32wo44a3yfdmjp7hmsflvtchui
Learning Data Augmentation with Online Bilevel Optimization for Image Classification
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This framework can be used as a general solution to learn the optimal data augmentation jointly with an end task model like a classifier. ...
Data augmentation is a key practice in machine learning for improving generalization performance. ...
In order to have differentiable affine and color transformations, we use the Kornia [43] library and the affine grid and grid samples functions of the torchvision package of pytorch framework. ...
arXiv:2006.14699v2
fatcat:bsolo6fsjneh3kknfbs3kbmccq
Meta Approach to Data Augmentation Optimization
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. ...
In this paper, we propose to optimize image recognition models and data augmentation policies simultaneously to improve the performance using gradient descent. ...
Differentiable Data Augmentation To differentiate through φ, MADAO adopts the differentiable data augmentation pipeline following [17] . ...
arXiv:2006.07965v1
fatcat:gje32fsvqnaelipg4n5wc5eq3e
Deep invariant networks with differentiable augmentation layers
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
It can incorporate any type of differentiable augmentation and be applied to a broad class of learning problems beyond computer vision. ...
State-of-the-art methods for learning data augmentation policies require held-out data and are based on bilevel optimization problems, which are complex to solve and often computationally demanding. ...
In this experiments, differentiable augmentations were implemented using the Kornia package Riba et al. [2020] , as well as the official code of Faster AutoAugment Hataya et al. [2020] . ...
arXiv:2202.02142v3
fatcat:mnkrxreyejgpfaho4fnweilidu
AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In particular, we include hyperparameters for augmentation, loss weights, and soft-labels that are jointly estimated using implicit differentiation. ...
AutoAugment has sparked an interest in automated augmentation methods for deep learning models. ...
The code is in PyTorch [27] with the Kornia library [30] for differentiable image operations. ...
arXiv:2103.05863v2
fatcat:dblc7apwxrd6tnjdjn6txclwfa
An overview of mixing augmentation methods and augmentation strategies
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2107.09887v1 fatcat:lvutkl3mszeqncl77dhobpxt7e
An alternative approach is application of data augmentation (DA) techniques that aim at model regularization by creating additional observations from the available ones. ...
First, the presented methods are briefly described, and then qualitatively compared with respect to their key characteristics. ...
Fourthly, differentiable augmentation operations from Kornia library [59] are used. ...
arXiv:2107.09887v2
fatcat:isue7dmwxzdihgwiq2efj3k3qm
Soft-Median Choice: An Automatic Feature Smoothing Method for Sound Event Detection
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To resolve these problems, we provide different channels of features smoothed to different extents along with the original feature, so the model can optimize the weights while cognizing all the errors. ...
Although the differentiable module of median blur with the backend of pytorch exists in kornia package[18], our study shows that a system with a differentiable median filter layer cannot converge well, ...
With the help of data-augmentation, enough quantity of data is obtained for training [3] [8] [9] . This technique improves generalization performance. ...
arXiv:2011.12564v3
fatcat:gljqxe6q3ravnnmorxzlm22ldu
A Benchmark and Baseline for Language-Driven Image Editing
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Not only performing well on challenging user data, but such an approach is also highly interpretable. ...
However, most similar work can only deal with a specific image domain or can only do global retouching. ...
.: Kornia: an open source differentiable computer vision library for pytorch (2020) 21 29. Gonzales, R.C., Woods, R.E.: Digital image processing (2002) 21 30. ...
arXiv:2010.02330v1
fatcat:7rz36nz2mjfknbxuwivd2a2pii
« Previous
Showing results 1 — 15 out of 37 results