1 code implementation • 28 May 2023 • Huizong Yang, Yuxin Sun, Ganesh Sundaramoorthi, Anthony Yezzi
We show analytically that as the representation power of the network increases, the optimization approaches a partial differential equation (PDE) in the continuum limit that is unstable.
no code implementations • 4 Jun 2022 • Yuxin Sun, Dong Lao, Ganesh Sundaramoorthi, Anthony Yezzi
We discover restrained numerical instabilities in current training practices of deep networks with stochastic gradient descent (SGD).
1 code implementation • 12 Dec 2021 • Zelin Zhang, Anthony Yezzi, Guillermo Gallego
Event cameras are novel bio-inspired sensors that measure per-pixel brightness differences asynchronously.
no code implementations • NeurIPS Workshop DLDE 2021 • Yuxin Sun, Dong Lao, Ganesh Sundaramoorthi, Anthony Yezzi
We introduce a recently developed framework PDE Acceleration, which is a variational approach to accelerated optimization with partial differential equations (PDE), in the context of optimization of deep networks.
no code implementations • 7 Jun 2021 • Navdeep Dahiya, Gourav Jhanwar, Anthony Yezzi, Masoud Zarepisheh, Saad Nadeem
Moreover, any changes in the clinical criteria requires a new set of manually generated plans by planners to build a new prediction model.
no code implementations • 27 Mar 2021 • Martin Mueller, Navdeep Dahiya, Anthony Yezzi
This paper proposes a novel training model based on shape and appearance features for object segmentation in images and videos.
1 code implementation • 9 Mar 2021 • Navdeep Dahiya, Sadegh R Alam, Pengpeng Zhang, Si-Yuan Zhang, Anthony Yezzi, Saad Nadeem
Treatment planning is done once at the beginning of the treatment using high-quality planning CT (pCT) images and manual contours for organs-at-risk (OARs) structures.
no code implementations • 19 Oct 2020 • Honglin Li, Yifei Fan, Frieder Ganz, Anthony Yezzi, Payam Barnaghi
The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs, which mislead a classifier to incorrect outputs in high confidence.
1 code implementation • 26 Nov 2019 • Chao Tang, Yifei Fan, Anthony Yezzi
The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs.
no code implementations • 7 Oct 2019 • Bipul Islam, Ji Liu, Anthony Yezzi, Romeil Sandhu
The ability to accurately reconstruct the 3D facets of a scene is one of the key problems in robotic vision.
no code implementations • CVPR 2019 • Anthony Yezzi, Ganesh Sundaramoorthi, Minas Benyamin
Following the seminal work of Nesterov, accelerated optimization methods have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimization strategies are either inapplicable or impractical.
no code implementations • NeurIPS 2018 • Ganesh Sundaramoorthi, Anthony Yezzi
Our approach evolves an infinite number of particles endowed with mass, represented as a mass density.
1 code implementation • 2 Oct 2018 • Jeff Calder, Anthony Yezzi
This paper provides a rigorous convergence rate and complexity analysis for a recently introduced framework, called PDE acceleration, for solving problems in the calculus of variations, and explores applications to obstacle problems.
Numerical Analysis Numerical Analysis Analysis of PDEs Dynamical Systems Optimization and Control 65M06, 35Q93, 65K10, 49K20
no code implementations • 4 Apr 2018 • Ganesh Sundaramoorthi, Anthony Yezzi
We present a new class of optimization methods, valid for any optimization problem setup on the space of diffeomorphisms by generalizing Nesterov accelerated optimization to the manifold of diffeomorphisms.
1 code implementation • 27 Jan 2018 • Yifei Fan, Anthony Yezzi
Two major uncertainties, dataset bias and adversarial examples, prevail in state-of-the-art AI algorithms with deep neural networks.
no code implementations • 27 Nov 2017 • Anthony Yezzi, Ganesh Sundaramoorthi
Following the seminal work of Nesterov, accelerated optimization methods have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimization strategies are either inapplicable or impractical.
no code implementations • CVPR 2017 • Naeemullah Khan, Byung-Woo Hong, Anthony Yezzi, Ganesh Sundaramoorthi
We formulate an energy for segmentation that is designed to have preference for segmenting the coarse over fine structure of the image, without smoothing across boundaries of regions.
no code implementations • CVPR 2015 • Naeemullah Khan, Marei Algarni, Anthony Yezzi, Ganesh Sundaramoorthi
Given a region of arbitrary shape in an image, these descriptors are formed from shape-dependent scale spaces of oriented gradients.
no code implementations • 6 Feb 2014 • Omar Arif, Ganesh Sundaramoorthi, Byung-Woo Hong, Anthony Yezzi
We illustrate the use of this motion estimation scheme in propagating a segmentation across frames and show that it leads to more accurate segmentation than traditional motion estimation that does not make use of physical constraints.
no code implementations • 3 Dec 2013 • Guillermo Gallego, Anthony Yezzi
We present a compact formula for the derivative of a 3-D rotation matrix with respect to its exponential coordinates.