arXiv subjects

Nicola Ferrier

Publications and source records attributed to Nicola Ferrier.

13 recordsLinked to original sources

arXiv2026

Cross-Platform Benchmark of Neural 3D Reconstruction for Autonomous Laboratory Robots

Autonomous robots performing laboratory tasks depend on 3D reconstruction pipelines that can turn raw camera streams into actionable object representations within the latency budget of a physical control loop. Neural 3D reconstruction methods have demonstrated high-quality view synthesis, but their real-time viability across the compute platforms on which laboratory robots actually run remains poorly characterized. In this work, we present a systematic compute-platform benchmark of neural 3D reconstruction methods, evaluating NeRF and 3D Gaussian Splatting training and rendering on GPU-enabled computing devices ranging from single-board computers to server-class nodes, and place Meta's SAM3D single-image reconstruction on the same axes to quantify its latency and fidelity gap relative to per-scene optimization. Our results show that Gaussian Splatting yields higher rendering quality than NeRF at greater GPU cost, and that onboard compute is insufficient for full per-scene optimization at interactive rates. Our preliminary assessment on SAM3D indicates that it delivers plausible object geometry within seconds, but with detail mismatches that can compromise downstream manipulation. Together, these findings motivate tiered pipelines in which lightweight feed-forward reconstruction sustains the real-time perception-and-tracking loop for laboratory robots, while heavier neural reconstruction is scheduled selectively on suitable compute.

cs.RO↗

arXiv2023

Scaling Computational Fluid Dynamics: In Situ Visualization of NekRS using SENSEI

In the realm of Computational Fluid Dynamics (CFD), the demand for memory and computation resources is extreme, necessitating the use of leadership-scale computing platforms for practical domain sizes. This intensive requirement renders traditional checkpointing methods ineffective due to the significant slowdown in simulations while saving state data to disk. As we progress towards exascale and GPU-driven High-Performance Computing (HPC) and confront larger problem sizes, the choice becomes increasingly stark: to compromise data fidelity or to reduce resolution. To navigate this challenge, this study advocates for the use of in situ analysis and visualization techniques. These allow more frequent data "snapshots" to be taken directly from memory, thus avoiding the need for disruptive checkpointing. We detail our approach of instrumenting NekRS, a GPU-focused thermal-fluid simulation code employing the spectral element method (SEM), and describe varied in situ and in transit strategies for data rendering. Additionally, we provide concrete scientific use-cases and report on runs performed on Polaris, Argonne Leadership Computing Facility's (ALCF) 44 Petaflop supercomputer and Jülich Wizard for European Leadership Science (JUWELS) Booster, Jülich Supercomputing Centre's (JSC) 71 Petaflop High Performance Computing (HPC) system, offering practical insight into the implications of our methodology.

cs.DC↗

arXiv2023

Adversarial Predictions of Data Distributions Across Federated Internet-of-Things Devices

Federated learning (FL) is increasingly becoming the default approach for training machine learning models across decentralized Internet-of-Things (IoT) devices. A key advantage of FL is that no raw data are communicated across the network, providing an immediate layer of privacy. Despite this, recent works have demonstrated that data reconstruction can be done with the locally trained model updates which are communicated across the network. However, many of these works have limitations with regard to how the gradients are computed in backpropagation. In this work, we demonstrate that the model weights shared in FL can expose revealing information about the local data distributions of IoT devices. This leakage could expose sensitive information to malicious actors in a distributed system. We further discuss results which show that injecting noise into model weights is ineffective at preventing data leakage without seriously harming the global model accuracy.

cs.LG↗

arXiv2021

A Two-stage Framework for Compound Figure Separation

Scientific literature contains large volumes of complex, unstructured figures that are compound in nature (i.e. composed of multiple images, graphs, and drawings). Separation of these compound figures is critical for information retrieval from these figures. In this paper, we propose a new strategy for compound figure separation, which decomposes the compound figures into constituent subfigures while preserving the association between the subfigures and their respective caption components. We propose a two-stage framework to address the proposed compound figure separation problem. In particular, the subfigure label detection module detects all subfigure labels in the first stage. Then, in the subfigure detection module, the detected subfigure labels help to detect the subfigures by optimizing the feature selection process and providing the global layout information as extra features. Extensive experiments are conducted to validate the effectiveness and superiority of the proposed framework, which improves the detection precision by 9%.

cs.CV↗

arXiv2021

EXSCLAIM! -- An automated pipeline for the construction of labeled materials imaging datasets from literature

Due to recent improvements in image resolution and acquisition speed, materials microscopy is experiencing an explosion of published imaging data. The standard publication format, while sufficient for traditional data ingestion scenarios where a select number of images can be critically examined and curated manually, is not conducive to large-scale data aggregation or analysis, hindering data sharing and reuse. Most images in publications are presented as components of a larger figure with their explicit context buried in the main body or caption text, so even if aggregated, collections of images with weak or no digitized contextual labels have limited value. To solve the problem of curating labeled microscopy data from literature, this work introduces the EXSCLAIM! Python toolkit for the automatic EXtraction, Separation, and Caption-based natural Language Annotation of IMages from scientific literature. We highlight the methodology behind the construction of EXSCLAIM! and demonstrate its ability to extract and label open-source scientific images at high volume.

cs.IR↗

arXiv2020

Toward an Automated HPC Pipeline for Processing Large Scale Electron Microscopy Data

We present a fully modular and scalable software pipeline for processing electron microscope (EM) images of brain slices into 3D visualization of individual neurons and demonstrate an end-to-end segmentation of a large EM volume using a supercomputer. Our pipeline scales multiple packages used by the EM community with minimal changes to the original source codes. We tested each step of the pipeline individually, on a workstation, a cluster, and a supercomputer. Furthermore, we can compose workflows from these operations using a Balsam database that can be triggered during the data acquisition or with the use of different front ends and control the granularity of the pipeline execution. We describe the implementation of our pipeline and modifications required to integrate and scale up existing codes. The modular nature of our environment enables diverse research groups to contribute to the pipeline without disrupting the workflow, i.e. new individual codes can be easily integrated for each step on the pipeline.

cs.DC↗

arXiv2019

Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping

Mapping all the neurons in the brain requires automatic reconstruction of entire cells from volume electron microscopy data. The flood-filling network (FFN) architecture has demonstrated leading performance for segmenting structures from this data. However, the training of the network is computationally expensive. In order to reduce the training time, we implemented synchronous and data-parallel distributed training using the Horovod library, which is different from the asynchronous training scheme used in the published FFN code. We demonstrated that our distributed training scaled well up to 2048 Intel Knights Landing (KNL) nodes on the Theta supercomputer. Our trained models achieved similar level of inference performance, but took less training time compared to previous methods. Our study on the effects of different batch sizes on FFN training suggests ways to further improve training efficiency. Our findings on optimal learning rate and batch sizes agree with previous works.

cs.DC↗

arXiv2019

Training on the Edge: The why and the how

Edge computing is the natural progression from Cloud computing, where, instead of collecting all data and processing it centrally, like in a cloud computing environment, we distribute the computing power and try to do as much processing as possible, close to the source of the data. There are various reasons this model is being adopted quickly, including privacy, and reduced power and bandwidth requirements on the Edge nodes. While it is common to see inference being done on Edge nodes today, it is much less common to do training on the Edge. The reasons for this range from computational limitations, to it not being advantageous in reducing communications between the Edge nodes. In this paper, we explore some scenarios where it is advantageous to do training on the Edge, as well as the use of checkpointing strategies to save memory.

cs.DC↗

arXiv2018

U-SLADS: Unsupervised Learning Approach for Dynamic Dendrite Sampling

Novel data acquisition schemes have been an emerging need for scanning microscopy based imaging techniques to reduce the time in data acquisition and to minimize probing radiation in sample exposure. Varies sparse sampling schemes have been studied and are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. Dynamic sparse sampling methods, particularly supervised learning based iterative sampling algorithms, have shown promising results for sampling pixel locations on the edges or boundaries during imaging. However, dynamic sampling for imaging skeleton-like objects such as metal dendrites remains difficult. Here, we address a new unsupervised learning approach using Hierarchical Gaussian Mixture Mod- els (HGMM) to dynamically sample metal dendrites. This technique is very useful if the users are interested in fast imaging the primary and secondary arms of metal dendrites in solidification process in materials science.

eess.IV↗

arXiv2018

SLADS-Net: Supervised Learning Approach for Dynamic Sampling using Deep Neural Networks

In scanning microscopy based imaging techniques, there is a need to develop novel data acquisition schemes that can reduce the time for data acquisition and minimize sample exposure to the probing radiation. Sparse sampling schemes are ideally suited for such applications where the images can be reconstructed from a sparse set of measurements. In particular, dynamic sparse sampling based on supervised learning has shown promising results for practical applications. However, a particular drawback of such methods is that it requires training image sets with similar information content which may not always be available. In this paper, we introduce a Supervised Learning Approach for Dynamic Sampling (SLADS) algorithm that uses a deep neural network based training approach. We call this algorithm SLADS- Net. We have performed simulated experiments for dynamic sampling using SLADS-Net in which the training images either have similar information content or completely different information content, when compared to the testing images. We compare the performance across various methods for training such as least- squares, support vector regression and deep neural networks. From these results we observe that deep neural network based training results in superior performance when the training and testing images are not similar. We also discuss the development of a pre-trained SLADS-Net that uses generic images for training. Here, the neural network parameters are pre-trained so that users can directly apply SLADS-Net for imaging experiments.

eess.SP↗

arXiv2018

Particle Tracking and Extended Object Imaging by Interferometric Super Resolution Microscopy

An interferometric fluorescent microscope and a novel theoretic image reconstruction approach were developed and used to obtain super-resolution images of live biological samples and to enable dynamic real time tracking. The tracking utilizes the information stored in the interference pattern of both the illuminating incoherent light and the emitted light. By periodically shifting the interferometer phase and a phase retrieval algorithm we obtain information that allow localization with sub-2 nm axial resolution at 5 Hz.

physics.optics↗

arXiv2017

Reduced Electron Exposure for Energy-Dispersive Spectroscopy using Dynamic Sampling

Analytical electron microscopy and spectroscopy of biological specimens, polymers, and other beam sensitive materials has been a challenging area due to irradiation damage. There is a pressing need to develop novel imaging and spectroscopic imaging methods that will minimize such sample damage as well as reduce the data acquisition time. The latter is useful for high-throughput analysis of materials structure and chemistry. In this work, we present a novel machine learning based method for dynamic sparse sampling of EDS data using a scanning electron microscope. Our method, based on the supervised learning approach for dynamic sampling algorithm and neural networks based classification of EDS data, allows a dramatic reduction in the total sampling of up to 90%, while maintaining the fidelity of the reconstructed elemental maps and spectroscopic data. We believe this approach will enable imaging and elemental mapping of materials that would otherwise be inaccessible to these analysis techniques.

cs.LG↗

arXiv2016

In-situ 3D Imaging of Catalysis Induced Strain in Gold Nanoparticles

Multi-electron transfer processes, such as hydrogen and oxygen evolution reactions, are crucially important in energy and biological science but require favorable catalysts to achieve fast kinetics. Nanostructuring catalysts can dramatically improve their properties, which can be difficult to understand due to strain and size dependent thermodynamics, the influence of defects, and substrate dependent activities. Here, we report 3D imaging of single gold nanoparticles during catalysis of ascorbic acid decomposition using Bragg coherent diffractive imaging (BCDI) as a route to eliminate ensemble effects while elucidating the strain-activity connection. Local strains were measured in single nanoparticles and modeled using reactive molecular dynamics (RMD) simulations and finite element analysis (FEA) simulations. RMD reveals a new chemical pathway for local strain generation in the gold lattice: chemisorption of hydroxyl ions. FEA reveals that the RMD results are transferable to the larger nanocrystal sizes studied in the experiment. Our study reveals the strain-activity connection and opens a powerful new avenue for joint theoretical and experimental studies of multi-electron transfer processes catalyzed by nanocrystals.

cond-mat.mtrl-sci↗