Deep Residual Network for Joint Demosaicing and Super- Resolution

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.

Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretiz ...

The different receptors in human skin show not only diversity in the stimuli to which they respond, but also variable sensitivity and directionality. This is often determined by their location or morphology, and can play an important role in filtering or a ...

Decision-making permeates every aspect of human and societal development, from individuals' daily choices to the complex decisions made by communities and institutions. Central to effective decision-making is the discipline of optimization, which seeks th ...

The goal of this paper is to characterize function distributions that general neural networks trained by descent algorithms (GD/SGD), can or cannot learn in polytime. The results are: (1) The paradigm of general neural networks trained by SGD is poly-time ...

Depleted Monolithic Active Pixel Sensor (DMAPS) sensors developed in the Tower Semiconductor 180 nm CMOS imaging process have been designed in the context of the ATLAS ITk upgrade Phase-II at the HL-LHC and for future collider experiments. The "MALTA-Czoch ...

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 ...

Deep neural networks trained on physical losses are emerging as promising surrogates for nonlinear numerical solvers. These tools can predict solutions to Maxwell's equations and compute gradients of output fields with respect to the material and geometric ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

The recent developments of deep learning cover a wide variety of tasks such as image classification, text translation, playing go, and folding proteins. All these successful methods depend on a gradient-based learning algorithm to train a model on massive ...

According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...

Non-linear partial differential Kolmogorov equations are successfully used to describe a wide range of time dependent phenomena, in natural sciences, engineering or even finance. For example, in physical systems, the Allen-Cahn equation describes pattern f ...

The material composition of asteroids is an essential piece of knowledge in the quest to understand the formation and evolution of the Solar System. Visual to near-infrared spectra or multiband photometry is required to constrain the material composition o ...

In this paper we explore deep learning models to monitor longitudinal liveability changes in Dutch cities at the neighbourhood level. Our liveability reference data is defined by a country-wise yearly survey based on a set of indicators combined into a liv ...

In recent years, new emerging immersive imaging modalities, e.g. light fields, have been receiving growing attention, becoming increasingly widespread over the years. Light fields are often captured through multi-camera arrays or plenoptic cameras, with th ...

Deep spiking neural networks (SNNs) offer the promise of low-power artificial intelligence. However, training deep SNNs from scratch or converting deep artificial neural networks to SNNs without loss of performance has been a challenge. Here we propose an ...

Cross-resolution face recognition has become a challenging problem for modern deep face recognition systems. It aims at matching a low-resolution probe image with high-resolution gallery images registered in a database. Existing methods mainly leverage pri ...

Vision systems built around conventional image sensors have to read, encode and transmit large quantities of pixel information, a majority of which is redundant. As a result, new computational imaging sensor architectures were developed to preprocess the r ...

The minimization of a data-fidelity term and an additive regularization functional gives rise to a powerful framework for supervised learning. In this paper, we present a unifying regularization functional that depends on an operator L\documentclass[12pt]{ ...

Deep Residual Network for Joint Demosaicing and Super- Resolution

Chat with Graph Search

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

Morphological and Material Programability of a Hall-Effect Based Soft Tactile Sensors

Reliable data-driven decision-making through optimal transport

Polynomial-time universality and limitations of deep learning

MALTA-Cz: a radiation hard full-size monolithic CMOS sensor with small electrodes on high-resistivity Czochralski substrate

Topics in statistical physics of high-dimensional machine learning

Predicting nonlinear optical scattering with physics-driven neural networks

Robust machine learning for neuroscientific inference

Transformer Models for Vision

Robust Training and Verification of Deep Neural Networks

Solving Non-linear Kolmogorov Equations in Large Dimensions by Using Deep Learning: A Numerical Comparison of Discretization Schemes

Euclid: Identification of asteroid streaks in simulated images using deep learning

Time Series Analysis of Urban Liveability

Towards learning-based denoising of light fields

An exact mapping from ReLU networks to spiking neural networks

Cross-resolution Face Recognition via Identity-Preserving Network and Knowledge Distillation

Computational Imaging SPAD Cameras

From Kernel Methods to Neural Networks: A Unifying Variational Formulation