TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

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.

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Orthogonal frequency-division multiplexing (OFDM) is widely used to mitigate inter-symbol interference (ISI) from multipath fading. However, the open nature of wireless OFDM systems makes them vulnerable to jamming attacks. In this context, pilot jamming i ...

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Machine learning has provided a means to accelerate early-stage drug discovery by combining molecule generation and filtering steps in a single architecture that leverages the experience and design preferences of medicinal chemists. However, designing mach ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

The rates of tropical deforestation remain high, resulting in carbon emissions, biodiversity loss, and impacts on local communities. To design effective policies to tackle this, it is necessary to know what the drivers behind deforestation are. Since drive ...

Cell segmentation is a critical step for quantitative single-cell analysis in microscopy images. Existing cell segmentation methods are often tailored to specific modalities or require manual interventions to specify hyper-parameters in different experimen ...

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Chattez avec Graph Search

Residual-based attention in physics-informed neural networks

Meta-learning to address diverse Earth observation problems across resolutions

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Adversarial Training for Jamming-Robust Channel Estimation in OFDM Systems

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Machine learning-aided generative molecular design

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Mapping drivers of tropical forest loss with satellite image time series and machine learning

The multimodality cell segmentation challenge: toward universal solutions

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Sparse autoregressive neural networks for classical spin systems

Aggregating Spatial and Photometric Context for Photometric Stereo

Revisiting Character-level Adversarial Attacks for Language Models

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Efficient local linearity regularization to overcome catastrophic overfitting

Incorporating Projective Geometry into Deep Learning