Community detection in graphs

S Fortunato - Physics reports, 2010 - Elsevier
The modern science of networks has brought significant advances to our understanding of
complex systems. One of the most relevant features of graphs representing real systems is …

A survey on underwater computer vision

SP González-Sabbagh, A Robles-Kelly - ACM Computing Surveys, 2023 - dl.acm.org
Underwater computer vision has attracted increasing attention in the research community
due to the recent advances in underwater platforms such as of rovers, gliders, autonomous …

Stochastic solutions for linear inverse problems using the prior implicit in a denoiser

Z Kadkhodaie, E Simoncelli - Advances in Neural …, 2021 - proceedings.neurips.cc
Deep neural networks have provided state-of-the-art solutions for problems such as image
denoising, which implicitly rely on a prior probability model of natural images. Two recent …

Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data

GK Dziugaite, DM Roy - arXiv preprint arXiv:1703.11008, 2017 - arxiv.org
One of the defining properties of deep learning is that models are chosen to have many
more parameters than available training data. In light of this capacity for overfitting, it is …

A general and adaptive robust loss function

JT Barron - Proceedings of the IEEE/CVF conference on …, 2019 - openaccess.thecvf.com
We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc,
generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By …

Graduated non-convexity for robust spatial perception: From non-minimal solvers to global outlier rejection

H Yang, P Antonante, V Tzoumas… - IEEE Robotics and …, 2020 - ieeexplore.ieee.org
Semidefinite Programming (SDP) and Sums-of-Squares (SOS) relaxations have led to
certifiably optimal non-minimal solvers for several robotics and computer vision problems …

An introduction to continuous optimization for imaging

A Chambolle, T Pock - Acta Numerica, 2016 - cambridge.org
A large number of imaging problems reduce to the optimization of a cost function, with
typical structural properties. The aim of this paper is to describe the state of the art in …

Sparse regularization via convex analysis

I Selesnick - IEEE Transactions on Signal Processing, 2017 - ieeexplore.ieee.org
Sparse approximate solutions to linear equations are classically obtained via L1 norm
regularized least squares, but this method often underestimates the true solution. As an …

Unnatural l0 sparse representation for natural image deblurring

L Xu, S Zheng, J Jia - … of the IEEE conference on computer …, 2013 - openaccess.thecvf.com
We show in this paper that the success of previous maximum a posterior (MAP) based blur
removal methods partly stems from their respective intermediate steps, which implicitly or …

Optical flow modeling and computation: A survey

D Fortun, P Bouthemy, C Kervrann - Computer Vision and Image …, 2015 - Elsevier
Optical flow estimation is one of the oldest and still most active research domains in
computer vision. In 35 years, many methodological concepts have been introduced and …