Publications related to Contrastive Class-aware Adaptation for Domain Generalization

Related publications (35)

How data structures affect generalization in Kernel Methods and Deep Learning

Artificial Intelligence has revolutionized numerous fields, driving advancements in healthcare, finance, and autonomous systems. At the core of this revolution lies Deep Learning---algorithms that learn representations from data through computational layer ...

EPFL2025

FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning

Zhuan Shi, Gang Wang

Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not well-suited for scenarios involving data and/or system ...

IJCAI2024

Domain adaptation via alignment of operation profile for Remaining Useful Lifetime prediction

Ismail Nejjar, Olga Fink, Mengjie Zhao

Effective Prognostics and Health Management (PHM) relies on accurate prediction of the Remaining Useful Life (RUL). Data-driven RUL prediction techniques rely heavily on the representativeness of the available time-to-failure trajectories. Therefore, these ...

Elsevier2024

Microbial electrochemical bioremediation of petroleum hydrocarbons (PHCs) pollution: Recent advances and outlook

Sami Rtimi

Soil contamination by petroleum hydrocarbons (PHCs) causes various acute problems such as crop growth, yield, and grain quality. Many Physico-chemical and biological approaches are employed to remove the PHCs from polluted soil. However, some of these appr ...

ELSEVIER SCIENCE SA2023

Improving Object Detection under Domain Shifts

Vidit Vidit

Object detection plays a critical role in various computer vision applications, encompassing domains like autonomous vehicles, object tracking, and scene understanding. These applica- tions rely on detectors that generate bounding boxes around known object ...

EPFL2023

Center-aware Adversarial Augmentation for Single Domain Generalization

Mathieu Salzmann

Domain generalization (DG) aims to learn a model from multiple training (i.e., source) domains that can generalize well to the unseen test (i.e., target) data coming from a different distribution. Single domain generalization (SingleDG) has recently emerge ...

IEEE COMPUTER SOC2023

Blue Brain Nexus: An open, secure, scalable system for knowledge graph management and data-driven science

Henry Markram, Henry Genet, Alejandra Garcia Rojas Martinez, Sean Lewis Hill, Huanxiang Lu, Mohameth François Sy, Samuel Claude Kerrien, Michaël Fernand Paul Dupont, Silvia Rosario Jimenez Tejeda, Bogdan Roman, Ian Lavriushev, Anna-Kristin Kaufmann, Didac Montero Mendez, Wojciech Adam Wajerowicz, Pierre-Alexandre Fonta, Kenneth William Pirman, Julien Antonin Machon, Jonathan Raël Lurie, Dhanesh Neela Mana, Natalia Stafeeva, Alexander Désiré Ulbrich, Carolina Johanna Elisabeth Lindqvist

Modern data-driven science often consists of iterative cycles of data discovery, acquisition, preparation, analysis, model building and validation leading to knowledge discovery as well as dissemination at scale. The unique challenges of building and simul ...

2023

AIDE: Accelerating image‐based ecological surveys with interactive machine learning

Devis Tuia, Benjamin Alexander Kellenberger

Ecological surveys increasingly rely on large‐scale image datasets, typically terabytes of imagery for a single survey. The ability to collect this volume of data allows surveys of unprecedented scale, at the cost of expansive volumes of photo‐interpretati ...

2020

Beyond Sharing Weights for Deep Domain Adaptation

Pascal Fua, Mathieu Salzmann, Artem Rozantsev

The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too expensive or impractic ...

2018

Slim: Explicit Slot-Intent Mapping With Bert For Joint Multi-Intent Detection And Slot Filling

Boi Faltings, Fei Mi

Utterance-level intent detection and token-level slot filling are two key tasks for spoken language understanding (SLU) in task-oriented systems. Most existing approaches assume that only a single intent exists in an utterance. However, there are often mul ...

IEEE2022

Surface Susceptibilities as Characteristic Models of Reflective Metasurfaces

Karim Achouri, Shourya Dutta Gupta, Ville Tuovi Tiukuvaara

While metasurfaces (MSs) are constructed from deeply subwavelength unit cells, they are generally electrically large and full-wave simulations of the complete structure are computationally expensive. Thus, to reduce this high computational cost, nonuniform ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Linking interactive optimization for urban planning with a semantic 3D city model

François Maréchal, Sébastien Cajot, Nils Christian Schüler

The cities in which we live are constantly evolving. The active management of this evolution is referred to as urban planning. The according development process could go in many directions resulting in a large number of potential future scenarios of a city ...

Copernicus GmbH2018

BactImAS: a platform for processing and analysis of bacterial time-lapse microscopy movies

Zeljka Maglica

Background: The software available to date for analyzing image sequences from time-lapse microscopy works only for certain bacteria and under limited conditions. These programs, mostly MATLAB-based, fail for microbes with irregular shape, indistinct cell d ...

Biomed Central Ltd2014

Design and validation of a multi-task, multi-context protocol for real-world gait simulation

Kamiar Aminian, Anisoara Ionescu

Background: Measuring mobility in daily life entails dealing with confounding factors arising from multiple sources, including pathological characteristics, patient specific walking strategies, environment/context, and purpose of the task. The primary aim ...

BioMed Central2022

Integrated, web-based information system to support collaborative resource management

François Golay, Jens Ingensand

In order to support a more effective and environmentally aware resource management, information systems may be designed to integrate relevant information and indicators about the resource and its environment and to make them available to all stakeholders a ...

2008

Elucidating the transition between CO2 physisorption and chemisorption in 1,2,4-triazolate ionic liquids at a molecular level

Paul Joseph Dyson, Zhaofu Fei, Xuemei Yang

Capture of CO2 is a crucial process to achieve carbon neutrality. High-performance CO2 capture involves both physi- and chemi-sorption, with a transition between them. However, the underlying mechanistic insights required to produce the methods to tune the ...

ELSEVIER SCIENCE SA2022

Model refactoring using transformations

Modern software is reaching levels of complexity encountered in biological systems; sometimes comprising systems of systems each of which may include tens of millions of lines of code. Model Driven Engineering (MDE) advocates raising the level of abstracti ...

EPFL2008

Online and Consistent Correlation Clustering

Andreas Maggiori

In the correlation clustering problem the input is a signed graph where the sign indicates whether each pair of points should be placed in the same cluster or not. The goal of the problem is to compute a clustering which minimizes the number of disagreemen ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

Concrete syntax definition for modeling languages

Frédéric Fondement

Model Driven Engineering (MDE) promotes the use of models as primary artefacts of a software development process, as an attempt to handle complexity through abstraction, e.g. to cope with the evolution of execution platforms. MDE follows a stepwise approac ...

EPFL2007

A case for co-construction with teachers in curricular reform: Introducing computer science in primary school

Francesco Mondada, Laila Abdelsalam El-Hamamsy, Jessica Elke Dehler Zufferey, Barbara Bruno, Helena Kovacs

With the introduction of Computer Science (CS) into curricula worldwide, researchers have investigated whether CS could be introduced transversally, as a support other disciplines. Few however consider both student learning and the teachers’ perspective in ...

ACM2022