Concept

Loi de Lévy

Publications associées (32)

Towards Robust Vision Transformer

Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard accuracy and com ...

IEEE COMPUTER SOC2022

OptTTA: Learnable Test-Time Augmentation for Source-Free Medical Image Segmentation Under Domain Shift

Jean-Philippe Thiran, Guillaume Marc Georges Vray, Devavrat Tomar

As distribution shifts are inescapable in realistic clinical scenarios due to inconsistencies in imaging protocols, scanner vendors, and across different centers, well-trained deep models incur a domain generalization problem in unseen environments. Despit ...

PMLR2022

Considerations on the partial safety factor format for reinforced concrete structures accounting for multiple failure modes

Aurelio Muttoni, Miguel Fernández Ruiz, Qianhui Yu

The increasing usage of nonlinear analyses for the design of reinforced concrete structures and the necessity of codes of practice to provide a consistent safety format for them is one of the challenges that new generations of codes of practice are facing. ...

ELSEVIER SCI LTD2022

Robustness and invariance properties of image classifiers

Apostolos Modas

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...

EPFL2022

Continual Test-Time Domain Adaptation

Olga Fink, Qin Wang

Test-time domain adaptation aims to adapt a source pretrained model to a target domain without using any source data. Existing works mainly consider the case where the target domain is static. However, real-world machine perception systems are running in n ...

IEEE COMPUTER SOC2022

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Daniel Kuhn, Andreas Krause, Tobias Sutter

Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribut ...

2021

Effect of collisions on non-adiabatic electron dynamics in ITG-driven microturbulence

Stephan Brunner, Justin Richard Ball

Non-adiabatic electron response leads to significant changes in ion temperature gradient (ITG) eigenmodes, leading, in particular, to fine-structures that are significantly extended along the magnetic field lines at corresponding mode rational surfaces (MR ...

AIP Publishing2021

Born to be different: the formation process of Cu nanoparticles tunes the size trend of the activity for CO2 to CH4 conversion

Kevin Rossi, Elena Gazzarrini

We investigate the impact of the formation process of Cu nanoparticles on the distribution of adsorption sites and hence on their activity. Using molecular dynamics, we model formation pathways characteristic of physical synthesis routes as the annealing o ...

ROYAL SOC CHEMISTRY2021

Multiple testing with test statistics following heavy-tailed distributions

Zhiwen Jiang

In multiple testing problems where the components come from a mixture model of noise and true effect, we seek to first test for the existence of the non-zero components, and then identify the true alternatives under a fixed significance level

\alpha

. Two ...

EPFL2021

Robustness via Cross-Domain Ensembles

Amir Roshan Zamir, Oguzhan Fatih Kar, Shuqing Teresa Yeo

We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong predi ...

IEEE2021

Graph Chatbot

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.

Connectez-vous pour utiliser Chat avec Graph Search

Multiple testing with test statistics following heavy-tailed distributions

Zhiwen Jiang

\alpha

. Two ...

EPFL2021