Towards Trustworthy Deep Learning for Image Reconstruction

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.

Traditional aerodynamic shape optimization (ASO) is costly and time-intensive, requiring extensive manual tuning for parameterization to define the design space and manipulate geometries. Conventional parameterization methods limit flexibility and demand s ...

When two objects are rubbed together, they create friction, heat, and their surfaces might be worn away. However, the fundamental mechanisms behind these processes remain poorly understood. While empirical engineering models exist, they are tailored to spe ...

Understanding the high-dimensional chaotic dynamics occurring in complex biological systems such as recurrent neural networks or ecosystems remains a conceptual challenge. For low-dimensional dynamics, fixed points provide the geometric scaffold of the dyn ...

This paper presents a model-agnostic search for narrow resonances in the dijet final state in the mass range 1.8-6 TeV. The signal is assumed to produce jets with substructure atypical of jets initiated by light quarks or gluons, with minimal additional as ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

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 ...

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 ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

In the domain of computational structural biology, predicting protein interactions based on molecular structure remains a pivotal challenge. This thesis delves into this challenge through a series of interconnected studies. The first chapter introduces th ...

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 ...

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

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 ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

The value of luxury goods, particularly investment-grade gemstones, is influenced by their origin and authenticity, often resulting in differences worth millions of dollars. Traditional methods for determining gemstone origin and detecting treatments invol ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

Towards Trustworthy Deep Learning for Image Reconstruction

Chat with Graph Search

Automated Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

Wear across scales

Fixed point geometry in chaotic neural networks

Model-agnostic Search for Dijet Resonances with Anomalous Jet Substructure in Proton-proton Collisions at S=13 Tev

Understanding generalization and robustness in modern deep learning

Aggregating Spatial and Photometric Context for Photometric Stereo

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

Topics in statistical physics of high-dimensional machine learning

Predicting protein interactions using geometric deep learning on protein surfaces

Efficient local linearity regularization to overcome catastrophic overfitting

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Incorporating Projective Geometry into Deep Learning

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Enabling Uncertainty Estimation in Iterative Neural Networks

GEMTELLIGENCE: Accelerating gemstone classification with deep learning

Random matrix methods for high-dimensional machine learning models

Partial discharge localization in power transformer tanks using machine learning methods

On the number of regions of piecewise linear neural networks