Publications associées à Scale-Adaptive Superpixels

Modular segmentation, spatial analysis and visualization of volume electron microscopy datasets

Volume electron microscopy is the method of choice for the in situ interrogation of cellular ultrastructure at the nanometer scale, and with the increase in large raw image datasets generated, improving computational strategies for image segmentation and s ...

Nature Portfolio2024

Detecting Anomalies and Obstacles in Road Scenes

Krzysztof Maciej Lis

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

EPFL2023

Role of Minimum Adhesive Wear Particle Size in Third-Body Layer Properties

Jean-François Molinari, Son-Jonathan Pham-Ba

We employ a novel discrete element method (DEM) force formulation to simulate adhesive wear and assess the effects of material and loading parameters on the properties of the third-body layer (TBL) formed during sliding motion. The study emphasizes the rol ...

2023

Design and Development of a Diagnostic System for a Non-Intercepting Direct Measure of the SPIDER Ion Source Beamlet Current

Stable and uniform beams with low divergence are required in particle accelerators; therefore, beyond the accelerated current, measuring the beam current spatial uniformity and stability over time is necessary to assess the beam performance, since these pa ...

MDPI2023

Beam homogeneity of caesium seeded SPIDER using a direct beamlet current measurement

The ITER Heating Neutral Beam (HNB) source prototype SPIDER (Source for the Production of Ions of Deuterium Extracted from a Radio frequency plasma), hosted at the Neutral Beam Test Facility (NBTF) in Padova, Italy, has recently started operating with evap ...

ELSEVIER SCIENCE SA2023

Transfer learning application of self-supervised learning in ARPES

Gabriel Aeppli

There is a growing recognition that electronic band structure is a local property of materials and devices, and there is steep growth in capabilities to collect the relevant data. New photon sources, from small-laboratory-based lasers to free electron lase ...

IOP Publishing Ltd2023

Confidence Matters: Applications to Semantic Segmentation

Prabhu Teja Sivaprasad

The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...

EPFL2023

MultiMAE: Multi-modal Multi-task Masked Autoencoders

Amir Roshan Zamir, Roman Christian Bachmann, David Mizrahi, Andrei Atanov

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

Latent Space Slicing for Enhanced Entropy Modeling in Learning-Based Point Cloud Geometry Compression

Touradj Ebrahimi, Davi Nachtigall Lazzarotto

The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research com ...

IEEE2022

Role of stochastic noise and generalization error in the time propagation of neural-network quantum states

Giuseppe Carleo

Neural-network quantum states (NQS) have been shown to be a suitable variational ansatz to simulate out-of-equilibrium dynamics in two-dimensional systems using timedependent variational Monte Carlo (t-VMC). In particular, stable and accurate time propagat ...

SCIPOST FOUNDATION2022

Determining crack kinematics from imaged crack patterns

Katrin Beyer, Amir Rezaie, Bryan German Pantoja Rosero, Ketson Roberto Maximiano Dos Santos

Determining the relationship between the cause of damage and the subsequent structural behavior of infrastructure systems requires an accurate characterization of the propagation of cracks, which represents the evolution of the damage state. When no inform ...

2022

EMC Impact of Disturbances Generated by Multiple Sources

Farhad Rachidi-Haeri, Marcos Rubinstein, Hamidreza Karami

In this paper, the impact of an increasing number of arbitrary electrical/electronic devices on the overall radiated emissions is investigated. Understanding and quantifying such an impact are prerequisites to the proper evaluation of electromagnetic compa ...

2022

Evaluation Criterion of Proton Exchange Membrane (ECPEM) fuel cells considering inserted porous media inside the gas flow channel

Jan Van Herle, Hossein Pourrahmani

The focus of this study is to evaluate the effects of porous media inside the gas flow channel of Proton Exchange Membrane Fuel Cells (PEMFC) on four different output parameters of voltage, power density, pressure drop, and Nusselt number (Nu) considering ...

PERGAMON-ELSEVIER SCIENCE LTD2022

Deep learning-based analysis of multiple sclerosis lesions with high and ultra-high field MRI

Francesco La Rosa

Multiple sclerosis (MS) is the most common demyelinating disease of the central nervous system and affects almost 3 million people worldwide. There is currently no cure for MS, and its symptoms, starting with fatigue and weakness, often progress over time ...

EPFL2022

Step Change Detection for Improved ROCOF Evaluation of Power System Waveforms

Mario Paolone, Asja Derviskadic, Guglielmo Frigo, Alexandra Cameron Karpilow

In the analysis of power grid waveforms, the presence of amplitude or phase steps can disrupt the estimation of frequency and rate-of-change-of-frequency (ROCOF). Standard methods based on phasor-models fail in the extraction of signal parameters during th ...

IEEE2022

Bootstrapping for Approximate Homomorphic Encryption with Negligible Failure-Probability by Using Sparse-Secret Encapsulation

Jean-Pierre Hubaux, Jean-Philippe Léonard Bossuat, Juan Ramón Troncoso-Pastoriza

Bootstrapping parameters for the approximate homomorphic-encryption scheme of Cheon et al., CKKS (Asiacrypt 17), are usually instantiated using sparse secrets to be efficient. However, using sparse secrets constrains the range of practical parameters withi ...

SPRINGER INTERNATIONAL PUBLISHING AG2022

Improving the Training of Compact Neural Networks for Visual Recognition

Shuxuan Guo

During the Artificial Intelligence (AI) revolution of the past decades, deep neural networks have been widely used and have achieved tremendous success in visual recognition. Unfortunately, deploying deep models is challenging because of their huge model s ...

EPFL2022

Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap

Florent Gérard Krzakala, Lenka Zdeborová, Bruno Loureiro, Luca Pesce, Bruno Loureiro

A simple model to study subspace clustering is the high-dimensional k -Gaussian mixture model where the cluster means are sparse vectors. Here we provide an exact asymptotic characterization of the statistically optimal reconstruction error in this model i ...

2022

Optimization Method for Extracting Stabilizer Geometry and Properties of REBCO Tapes

Bertrand Dutoit, Bertrand Dutoit, Francesco Grilli, Arooj Akbar, Nicolo' Riva

A good knowledge of material properties is a critical aspect for modeling high-temperature superconductor (HTS) devices. However, the electrical resistivity of coated conductors above the critical current is limited. The major challenge in characterizing t ...

2021

Counting People by Estimating People Flows

Pascal Fua, Mathieu Salzmann, Weizhe Liu

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

2022