Contrastive Class-aware Adaptation for Domain Generalization

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

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 ...

Contrastive Class-aware Adaptation for Domain Generalization

Chattez avec Graph Search

How data structures affect generalization in Kernel Methods and Deep Learning

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

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

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

Improving Object Detection under Domain Shifts

Center-aware Adversarial Augmentation for Single Domain Generalization

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

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

Beyond Sharing Weights for Deep Domain Adaptation

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

Surface Susceptibilities as Characteristic Models of Reflective Metasurfaces

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

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

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

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

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

Model refactoring using transformations

Online and Consistent Correlation Clustering

Concrete syntax definition for modeling languages

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