Related papers: Single-shot self-supervised particle tracking

Single-shot self-supervised particle tracking

URL: http://arxiv.org/abs/2202.13546v1
Date: Mon, 28 Feb 2022 05:02:20 GMT
Title: Single-shot self-supervised particle tracking
Authors: Benjamin Midtvedt and Jes\'us Pineda and Fredrik Sk\"arberg and Erik Ols\'en and Harshith Bachimanchi and Emelie Wes\'en and Elin K. Esbj\"orner and Erik Selander and Fredrik H\"o\"ok and Daniel Midtvedt and Giovanni Volpe
Abstract summary: We propose a novel deep-learning method that learns to track objects with sub-pixel accuracy from a single unlabeled image. We demonstrate that LodeSTAR outperforms traditional methods in terms of accuracy. Thanks to the ability to train deep-learning models with a single unlabeled image, LodeSTAR can accelerate the development of high-quality microscopic analysis pipelines.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Particle tracking is a fundamental task in digital microscopy. Recently, machine-learning approaches have made great strides in overcoming the limitations of more classical approaches. The training of state-of-the-art machine-learning methods almost universally relies on either vast amounts of labeled experimental data or the ability to numerically simulate realistic datasets. However, the data produced by experiments are often challenging to label and cannot be easily reproduced numerically. Here, we propose a novel deep-learning method, named LodeSTAR (Low-shot deep Symmetric Tracking And Regression), that learns to tracks objects with sub-pixel accuracy from a single unlabeled experimental image. This is made possible by exploiting the inherent roto-translational symmetries of the data. We demonstrate that LodeSTAR outperforms traditional methods in terms of accuracy. Furthermore, we analyze challenging experimental data containing densely packed cells or noisy backgrounds. We also exploit additional symmetries to extend the measurable particle properties to the particle's vertical position by propagating the signal in Fourier space and its polarizability by scaling the signal strength. Thanks to the ability to train deep-learning models with a single unlabeled image, LodeSTAR can accelerate the development of high-quality microscopic analysis pipelines for engineering, biology, and medicine.

Related papers

Hyperspectral Lightcurve Inversion for Attitude Determination [0.9820957505036108]
Time series single-pixel spectral measurements of spacecraft are used to infer the spacecraft's attitude and rotation. The aim is to work with minimal information, thus no prior is available on the attitude nor on the inertia tensor. Results are shown based on synthetic data.
arXiv Detail & Related papers (2023-12-19T16:06:50Z)
Learning and Controlling Silicon Dopant Transitions in Graphene using Scanning Transmission Electron Microscopy [58.51812955462815]
We introduce a machine learning approach to determine the transition dynamics of silicon atoms on a single layer of carbon atoms. The data samples are processed and filtered to produce symbolic representations, which we use to train a neural network to predict transition probabilities. These learned transition dynamics are then leveraged to guide a single silicon atom throughout the lattice to pre-determined target destinations.
arXiv Detail & Related papers (2023-11-21T21:51:00Z)
Gradient-Based Feature Learning under Structured Data [57.76552698981579]
In the anisotropic setting, the commonly used spherical gradient dynamics may fail to recover the true direction. We show that appropriate weight normalization that is reminiscent of batch normalization can alleviate this issue. In particular, under the spiked model with a suitably large spike, the sample complexity of gradient-based training can be made independent of the information exponent.
arXiv Detail & Related papers (2023-09-07T16:55:50Z)
Manifold Learning with Sparse Regularised Optimal Transport [0.17205106391379024]
Real-world datasets are subject to noisy observations and sampling, so that distilling information about the underlying manifold is a major challenge. We propose a method for manifold learning that utilises a symmetric version of optimal transport with a quadratic regularisation. We prove that the resulting kernel is consistent with a Laplace-type operator in the continuous limit, establish robustness to heteroskedastic noise and exhibit these results in simulations.
arXiv Detail & Related papers (2023-07-19T08:05:46Z)
Closing the loop: Autonomous experiments enabled by machine-learning-based online data analysis in synchrotron beamline environments [80.49514665620008]
Machine learning can be used to enhance research involving large or rapidly generated datasets. In this study, we describe the incorporation of ML into a closed-loop workflow for X-ray reflectometry (XRR) We present solutions that provide an elementary data analysis in real time during the experiment without introducing the additional software dependencies in the beamline control software environment.
arXiv Detail & Related papers (2023-06-20T21:21:19Z)
Time Varying Particle Data Feature Extraction and Tracking with Neural Networks [20.825102707056647]
We take a deep learning approach to create feature representations for scientific particle data to assist feature extraction and tracking. We employ a deep learning model, which produces latent vectors to represent the relation between spatial locations and physical attributes in a local neighborhood. To achieve fast feature tracking, the mean-shift tracking algorithm is applied in the feature space.
arXiv Detail & Related papers (2021-05-27T15:38:14Z)
Dominant motion identification of multi-particle system using deep learning from video [0.0]
In this work, we provide a deep-learning framework that extracts relevant information from real-world videos of highly systems. We demonstrate this approach on videos of confined multi-agent/particle systems of ants, termites, fishes. Furthermore, we explore how these seemingly diverse systems have predictable underlying behavior.
arXiv Detail & Related papers (2021-04-26T17:10:56Z)
Unsupervised machine learning of topological phase transitions from experimental data [52.77024349608834]
We apply unsupervised machine learning techniques to experimental data from ultracold atoms. We obtain the topological phase diagram of the Haldane model in a completely unbiased fashion. Our work provides a benchmark for unsupervised detection of new exotic phases in complex many-body systems.
arXiv Detail & Related papers (2021-01-14T16:38:21Z)
Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation [63.94623495501023]
We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data. Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
arXiv Detail & Related papers (2020-10-20T08:36:51Z)
Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning [80.20302993614594]
We provide a statistical analysis to overcome drawbacks of Laplacian regularization. We unveil a large body of spectral filtering methods that exhibit desirable behaviors. We provide realistic computational guidelines in order to make our method usable with large amounts of data.
arXiv Detail & Related papers (2020-09-09T14:28:54Z)
A machine learning-based method for estimating the number and orientations of major fascicles in diffusion-weighted magnetic resonance imaging [7.032850705203263]
We propose a machine-based technique that can accurately estimate fascicles in voxel. Our method can be trained with either simulated or real measurements.
arXiv Detail & Related papers (2020-06-19T13:07:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.