Center-aware Adversarial Augmentation for Single Domain Generalization

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This paper presents a novel hybrid framework for generating and updating a synthetic population. We call it hybrid because it combines model-based and data-driven approaches. Existing generators produce a snapshot of synthetic data that becomes outdated ov ...

In this thesis we will present two results on global existence for nonlinear dispersive equations with data at or below the scaling regularity. In chapter 1 we take a probabilistic perspective to study the energy-critical nonlinear Schrödinger equation in ...

The ongoing electrification of the transportation fleet will increase the load on the electric power grid. Since both the transportation network and the power grid already experience periods of significant stress, joint analyses of both infrastructures wil ...

Given the patchy nature of gas plumes and the slow response of conventional gas sensors, the use of mobile robots for Gas Source Localization (GSL) tasks presents significant challenges. These aspects increase the difficulties in obtaining gas measurements ...

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Exploiting the recent advancements in artificial intelligence, showcased by ChatGPT and DALL-E, in real-world applications necessitates vast, domain-specific, and publicly accessible datasets. Unfortunately, the scarcity of such datasets poses a significan ...

Deep-learning-based digital twins (DDT) are a promising tool for data-driven system health management because they can be trained directly on operational data. A major challenge for efficient training however is that industrial datasets remain unlabeled. T ...

Bioaerosols are emitted from various sources into the indoor environment and can positively and negatively impact human health. Humans are the major source of bioaerosol emissions indoors, specifically for bacteria. However, efficient sampling to guarantee ...

The recent geopolitical conflicts in Europe highlighted the sensibility of the current energy system to the volatility of energy carrier prices. In the prospect of defining robust energy system configurations to ensure energy supply stability, it is necess ...

Tensor trains are a versatile tool to compress and work with high-dimensional data and functions. In this work we introduce the streaming tensor train approximation (STTA), a new class of algorithms for approximating a given tensor ' in the tensor train fo ...

Center-aware Adversarial Augmentation for Single Domain Generalization

Chat with Graph Search

Hybrid Simulator for Capturing Dynamics of Synthetic Populations

Probabilistic and Deterministic Wellposedness for Low Regularity Dispersive Equations

GreenEVT: Greensboro Electric Vehicle Testbed

Sense in Motion with Belief Clustering: Efficient Gas Source Localization with Mobile Robots

On the Generalization of Stochastic Gradient Descent with Momentum

Dated: Guidelines for Creating Synthetic Datasets for Engineering Design Applications

A Study on Gradient-based Meta-learning for Robust Deep Digital Twins

Comparison of two methods for bioaerosol sampling and characterization in a low-biomass chamber environment

Identification of typical district configurations: A two-step global sensitivity analysis framework

STREAMING TENSOR TRAIN APPROXIMATION