Publications associées à Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification

Publications associées (23)

Transfer learning-based approach for evaluating residual stiffness in carbon fiber reinforced composites and adhesives

This work proposes a transfer learning-based encoder-decoder framework to predict the relationship between loading conditions and residual stiffness in carbon fiber reinforced composites and adhesives. The encoder, built from a Convolutional Neural Network ...

2025

Correlation of the L-mode density limit with edge collisionality

Alessandro Pau

The 'density limit' is one of the fundamental bounds on tokamak operating space, and is commonly estimated via the empirical Greenwald scaling. This limit has garnered renewed interest in recent years as it has become clear that ITER and many tokamak pilot ...

IOP Publishing Ltd2025

Development of a blind control occupant behaviour model (BC-OBM) based on contextual and time-related factors through supervised machine learning approaches

Andrew James Sonta

Blind use patterns significantly impact visual comfort and energy efficiency in office buildings. To quantify this impact on building performance, blind control occupant behaviour models (BC-OBMs) are typically integrated into building performance simulati ...

2025

Smart Edge for Hierarchical Vision Systems

Yamin Sepehri

Deep neural networks provide magnificent results for vision tasks. However, their complex structures and numerous parameters make them computationally and memory-wise intensive. Execution of these models on resource-constrained, camera-equipped devices suc ...

EPFL2024

Joint Subject-Identification and Task-Decoding From Inferred Functional Brain Graphs Via a Multi-Task Neural Network

Elif Sema Balcioglu, Berkay Döner, Dimitri Nestor Alice Van De Ville, Hamid Behjat, Ekansh Sareen

Functional connectivity (FC) between brain regions as manifested via fMRI entails signatures that can be used to differentiate individuals and decode cognitive tasks. In this work, we use methods from graph structure inference to estimate FC, which is in c ...

IEEE Computer Society2024

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

Loris Di Natale

Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...

EPFL2024

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Seyed Mohammad Mahdi Johari

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

EPFL2024

Sparse representations, inference and learning

Emanuele Troiani

In recent years statistical physics has proven to be a valuable tool to probe into large dimensional inference problems such as the ones occurring in machine learning. Statistical physics provides analytical tools to study fundamental limitations in their ...

IOP Publishing Ltd2024

Probabilistic methods for neural combinatorial optimization

Nikolaos Karalias

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

EPFL2023

Visual question answering from another perspective: CLEVR mental rotation tests *

Sina Honari

Different types of mental rotation tests have been used extensively in psychology to understand human visual reasoning and perception. Understanding what an object or visual scene would look like from another viewpoint is a challenging problem that is made ...

ELSEVIER SCI LTD2023

Acoustic emission for the prediction of processing regimes in Laser Powder Bed Fusion, and the generation of processing maps

Roland Logé, Jamasp Jhabvala, Charlotte Léopoldine de Formanoir de la Cazerie, Rita Drissi Daoudi

The Laser Power Bed Fusion (LPBF) process is of high interest to many industries, such as motors and vehicles, robotics, biomedical applications, aerospace, and others. LPBF workpieces can indeed achieve near full density and high resistance. However, a la ...

ELSEVIER2023

Generating Controlled Physics-Informed Time-to-failure Trajectories for Prognostics in Unseen Operational Conditions

Olga Fink

Limited availability of representative time-to-failure (TTF) trajectories either limits the performance of deep learning (DL)-based approaches on remaining useful life (RUL) prediction in practice or even precludes their application. Generating synthetic d ...

Research Publishing2023

Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understanding

Mutian He

Recently, large pretrained language models have demonstrated strong language understanding capabilities. This is particularly reflected in their zero-shot and in-context learning abilities on downstream tasks through prompting. To assess their impact on sp ...

Isca-Int Speech Communication Assoc2023

Performance of Social Machine Learning under Limited Data

Ali H. Sayed, Virginia Bordignon, Mert Kayaalp, Ping Hu

This paper studies the non-Asymptotic classification performance of the social machine learning strategy. This strategy involves an independent training phase followed by a cooperative inference phase to classify a growing number of samples. By considering ...

IEEE2023

Improving K-means Clustering Using Speculation

Stefan Igescu, Anastasia Ailamaki, Viktor Sanca, Eleni Zapridou

K-means is one of the fundamental unsupervised data clustering and machine learning methods. It has been well studied over the years: parallelized, approximated, and optimized for different cases and applications. With increasingly higher parallelism leadi ...

2023

AI-based forecasting for optimised solar energy management and smart grid efficiency

Mostafa Nick, Amin Kaboli

This paper considers two pertinent research inquiries: 'Can an AI-based predictive framework be utilised for the optimisation of solar energy management?' and 'What are the ways in which the AI-based predictive framework can be integrated within the Smart ...

Taylor & Francis Ltd2023

Learning to Align Sequential Actions in the Wild

Pascal Fua, Bugra Tekin, Weizhe Liu

State-of-the-art methods for self-supervised sequential action alignment rely on deep networks that find correspon- dences across videos in time. They either learn frame-to- frame mapping across sequences, which does not leverage temporal information, or a ...

IEEE COMPUTER SOC2022

A hardware/software co-design vision for deep learning at the edge

David Atienza Alonso, Giovanni Ansaloni, Alexandre Sébastien Julien Levisse, Miguel Peon Quiros, Flavio Ponzina, Marco Antonio Rios, Benoît Walter Denkinger, Simone Machetti

The growing popularity of edgeAI requires novel solutions to support the deployment of compute-intense algorithms in embedded devices. In this article, we advocate for a holistic approach, where application-level transformations are jointly conceived with ...

2022

Photonic waveguide bundles using 3D laser writing and deep neural network image reconstruction

Demetri Psaltis, Niyazi Ulas Dinç, Giulia Panusa

In recent years, three-dimensional (3D) printing with multi-photon laser writing has become an essential tool fur the manufacturing of three-dimensional optical elements. Single-mode optical waveguides are one of the fundamental photonic components, and ar ...

OPTICAL SOC AMER2022

Microengineered devices enable long-term imaging of the ventral nerve cord in behaving adult Drosophila

Mahmut Selman Sakar, Pavan P Ramdya, Murat Kaynak, Semih Günel, Chin-Lin Chen, Florian Aymanns, Victor Lobato Rios, Jonas Friedrich Braun, Laura Joan Hermans

The dynamics and connectivity of neural circuits continuously change on timescales ranging from milliseconds to an animal's lifetime. Therefore, to understand biological networks, minimally invasive methods are required to repeatedly record them in behavin ...

Nature Research2022