Filters








13 Hits in 5.1 sec

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch [article]

Edgar Riba, Dmytro Mishkin, Daniel Ponsa, Ethan Rublee, Gary Bradski
2019 arXiv   pre-print
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.  ...  This paper introduces Kornia, an open source computer vision library built on top of PyTorch that will help students, researchers, companies and entrepreneurs to implement computer vision applications  ... 
arXiv:1910.02190v2 fatcat:shnrjgnvyfbgzaskdjznlb6psu

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

Edgar Riba, Dmytro Mishkin, Daniel Ponsa, Ethan Rublee, Gary Bradski
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
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.  ...  This paper introduces Kornia, an open source computer vision library built on top of PyTorch that will help students, researchers, companies and entrepreneurs to implement computer vision applications  ... 
doi:10.1109/wacv45572.2020.9093363 dblp:conf/wacv/RibaMPRB20 fatcat:dtyl4bijcfee3dv7se3hhgfmpa

A survey on Kornia: an Open Source Differentiable Computer Vision Library for PyTorch [article]

E. Riba, D. Mishkin, J. Shi, D. Ponsa, F. Moreno-Noguer, G. Bradski
2020 arXiv   pre-print
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.  ...  The folks from the Open Source Vision Foundation and OpenCV.org, and the PyTorch open-source community for helpful contributions and feedback.  ... 
arXiv:2009.10521v1 fatcat:wjyp5nzbfzfmjpvuxfaxydh5ra

Differentiable Data Augmentation with Kornia [article]

Jian Shi, Edgar Riba, Dmytro Mishkin, Francesc Moreno, Anguelos Nicolaou
2020 arXiv   pre-print
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

Differentiable Computational Geometry for 2D and 3D machine learning [article]

Yuanxin Zhong
2020 arXiv   pre-print
We present an optimized Differentiable Geometry Algorithm Library (DGAL) loaded with implementations of differentiable operators for geometric primitives like lines and polygons.  ...  With the growth of machine learning algorithms with geometry primitives, a high-efficiency library with differentiable geometric operators are desired.  ...  Kornia is a differentiable computer vision library equipped with differentiable transformation operations widely used in computer vision applications.  ... 
arXiv:2011.11134v1 fatcat:hlt2qhd4tbeebk7ysxtccruhnu

Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research [article]

Krishna Murthy Jatavallabhula, Edward Smith, Jean-Francois Lafleche, Clement Fuji Tsang, Artem Rozantsev, Wenzheng Chen, Tommy Xiang, Rev Lebaredian, Sanja Fidler
2019 arXiv   pre-print
We present Kaolin, a PyTorch library aiming to accelerate 3D deep learning research. Kaolin provides efficient implementations of differentiable 3D modules for use in deep learning systems.  ...  Kaolin is available as open-source software at https://github.com/NVIDIAGameWorks/kaolin/.  ...  Acknowledgments The authors would like to thank Amlan Kar for suggesting the need for this library. We also thank Ankur Handa for his advice during the initial and final stages of the project.  ... 
arXiv:1911.05063v2 fatcat:2mbh3eqljrfv5ervwrwtcu54ry

Self-Distilled Hashing for Deep Image Retrieval [article]

Young Kyun Jang, Geonmo Gu, Byungsoo Ko, Nam Ik Cho
2021 arXiv   pre-print
window7 224, from timm 2 open source library respectively.  ...  Algorithm 1 PyTorch-like pseudo-code details. # Import pytorch import torch as T # Import kornia library for augmentation # https://https://github.com/kornia/kornia import kornia.augmentation as Kg # Augmentation  ...  Self-Distilled Hashing for Deep Image Retrieval Supplementary Material  ... 
arXiv:2112.08816v1 fatcat:32wo44a3yfdmjp7hmsflvtchui

RANSAC-Flow: generic two-stage image alignment [article]

Xi Shen, François Darmon, Alexei A. Efros, Mathieu Aubry
2020 arXiv   pre-print
Fine alignment is learned in an unsupervised way by a deep network which optimizes a standard structural similarity metric (SSIM) between the two images, plus cycle-consistency.  ...  results on a range of tasks and datasets, including unsupervised optical flow on KITTI, dense correspondences on Hpatches, two-view geometry estimation on YFCC100M, localization on Aachen Day-Night, and, for  ...  We thank Shiry Ginosar, Thibault Groueix and Michal Irani for helpful discussions, and Elizabeth Alice Honig for her help in building the Brueghel dataset.  ... 
arXiv:2004.01526v2 fatcat:ltpp6c4gcnfmdo3pxdt2ulqqp4

Consensus Clustering With Unsupervised Representation Learning [article]

Jayanth Reddy Regatti, Aniket Anand Deshmukh, Eren Manavoglu, Urun Dogan
2021 arXiv   pre-print
on some popular computer vision datasets.  ...  In this work, we study the clustering ability of BYOL and observe that features learnt using BYOL may not be optimal for clustering.  ...  The color transformations were computed using Kornia [32] which is a differentiable computer vision library for Pytorch.  ... 
arXiv:2010.01245v2 fatcat:cwsojtbd2bbhxmpr7jpahymfwm

A Benchmark and Baseline for Language-Driven Image Editing [article]

Jing Shi, Ning Xu, Trung Bui, Franck Dernoncourt, Zheng Wen, Chenliang Xu
2020 arXiv   pre-print
Not only performing well on challenging user data, but such an approach is also highly interpretable.  ...  Riba, E., Mishkin, D., Ponsa, D., Rublee, E., Bradski, G.: Kornia: an open source differentiable computer vision library for pytorch (2020) 21 29.  ...  However, remove bg is non-differentiable thus would blocked the gradient backpropagation. And inpaint obj is a large network that is computational expensive for gradient.  ... 
arXiv:2010.02330v1 fatcat:7rz36nz2mjfknbxuwivd2a2pii

Online Invariance Selection for Local Feature Descriptors [article]

Rémi Pautrat, Viktor Larsson, Martin R. Oswald, Marc Pollefeys
2020 arXiv   pre-print
Our approach, named Local Invariance Selection at Runtime for Descriptors (LISRD), enables descriptors to adapt to adverse changes in images, while remaining discriminative when invariance is not required  ...  We propose to overcome this limitation with a disentanglement of invariance in local descriptors and with an online selection of the most appropriate invariance given the context.  ...  This work has been supported by an ETH Zurich Postdoctoral Fellowship and Innosuisse funding (Grant No. 34475.1 IP-ICT).  ... 
arXiv:2007.08988v3 fatcat:6byvawx4unbbthjanysrnaxdgi

Generating Unrestricted Adversarial Examples via Three Parameters [article]

Hanieh Naderi and Leili Goli and Shohreh Kasaei
2021 arXiv   pre-print
Experimental results show that the proposed adversarial examples obtain an average success rate of 93.5 also reduces the model accuracy by an average of 73 FMNIST, SVHN, CIFAR10, CIFAR100, and ImageNet  ...  The attack selects three points on the input image and based on their locations transforms the image into an adversarial example.  ...  Seyed-Mohsen Moosavi-Dezfooli for the helpful discussions.  ... 
arXiv:2103.07640v1 fatcat:wgid6cginjgd3offl6hwezwwaa

Decentralized Attribution of Generative Models [article]

Changhoon Kim, Yi Ren, Yezhou Yang
2021 arXiv   pre-print
We develop sufficient conditions of the keys that guarantee an attributability lower bound. Our method is validated on MNIST, CelebA, and FFHQ datasets.  ...  Neither does it provide an attributability guarantee. To this end, this paper studies decentralized attribution, which relies on binary classifiers associated with each user-end model.  ...  We would like to express our gratitude to Ni Trieu (ASU) for providing us invaluable advice, and Zhe Wang, Joshua Feinglass, Sheng Cheng, Yongbaek Cho and Huiliang Shao for helpful comments.  ... 
arXiv:2010.13974v4 fatcat:mb2wgo2mmfdt3kmb6i6y3u4pki