FreePoint: Unsupervised Point Cloud Instance Segmentation
May 11, 2023
| | | |
Computer Science
Computer Vision and Pattern Recognition
Instance segmentation of point clouds is a crucial task in 3D field with
numerous applications that involve localizing and segmenting objects in a
scene. However, achieving satisfactory results requires a large number of
manual annotations,...
Parasite infection in a cell population: role of the partitioning kernel
May 11, 2023
|
Mathematics
Quantitative Biology
Probability
Populations and Evolution
We consider a cell population subject to a parasite infection. Cells divide
at a constant rate and, at division, share the parasites they contain between
their two daughter cells. The sharing may be asymmetrical, and its law may
depend on t...
Partial separability and symplectic-Haantjes manifolds
May 11, 2023
| |
Physics
Mathematics
Mathematical Physics
Mathematical Physics
Symplectic Geometry
A theory of partial separability for classical Hamiltonian systems is
proposed in the context of Haantjes geometry.
As a general result, we show that the knowledge of a non-semisimple
symplectic-Haantjes manifold for a given Hamiltonian s...
Control sets on maximal compact subgroups
May 11, 2023
|
Mathematics
Dynamical Systems
Optimization and Control
In this paper we study the action of semigroups with nonempty interior of
noncompact connected semisimple Lie groups, with finite center, on their
maximal compact connected subgroups. As main results we describe the set of
transitivity of a...
Neural Wave Functions for Superfluids
May 11, 2023
| | | | | |
Physics
Computer Science
Quantum Gases
Superconductivity
Machine Learning
Computational Physics
Understanding superfluidity remains a major goal of condensed matter physics.
Here we tackle this challenge utilizing the recently developed Fermionic neural
network (FermiNet) wave function Ansatz [D. Pfau et al., Phys. Rev. Res. 2,
033429...
Backdoor Attack with Sparse and Invisible Trigger
May 11, 2023
| | | | |
Computer Science
Computer Vision and Pattern Recognition
Cryptography and Security
Machine Learning
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the
adversary manipulates a small portion of training data such that the victim
model predicts normally on the benign samples but classifies the triggered
samples as the ...
NUBO: A Transparent Python Package for Bayesian Optimization
May 11, 2023
| |
Computer Science
Statistics
Machine Learning
Mathematical Software
Machine Learning
NUBO, short for Newcastle University Bayesian Optimization, is a Bayesian
optimization framework for optimizing expensive-to-evaluate black-box
functions, such as physical experiments and computer simulators. Bayesian
optimization is a cost...
On the Dynamical Hierarchy in Gathering Protocols with Circulant
Topologies
May 11, 2023
| |
Mathematics
Dynamical Systems
In this article we investigate the convergence behavior of gathering
protocols with fixed circulant topologies using tools form dynamical systems.
Given a fixed number of mobile entities moving in the Euclidean plane, we model
a (linear) ga...
Rokhlin Dimension: Permanence Properties and Ideal Separation
May 11, 2023
|
Mathematics
Operator Algebras
Functional Analysis
We study the Rokhlin dimension for actions of residually finite groups on
C*-algebras. We give a definition equivalent to the original one due to Szabo,
Wu and Zacharias. We then prove a number of permanence properties and discuss
actions o...
Convolutional Neural Networks Rarely Learn Shape for Semantic
Segmentation
May 11, 2023
|
Computer Science
Computer Vision and Pattern Recognition
Shape learning, or the ability to leverage shape information, could be a
desirable property of convolutional neural networks (CNNs) when target objects
have specific shapes. While some research on the topic is emerging, there is no
systemat...