Wasserstein Adversarial Regularization for learning with label noise

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (31)

On the robustness of randomized classifiers to adversarial examples

Rafaël Benjamin Pinot

This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (i.e. classifiers that output random variables) and provide a thorough analysis of their behavior through the lens of statistical learning theo ...

SPRINGER2022

Deep learning-based galaxy image deconvolution

Frédéric Courbin, Pascale Jablonka, Jean-Luc Starck, Utsav Akhaury, Kevin Michalewicz

With the onset of large-scale astronomical surveys capturing millions of images, there is an increasing need to develop fast and accurate deconvolution algorithms that generalize well to different images. A powerful and accessible deconvolution method woul ...

FRONTIERS MEDIA SA2022

Local Kernel Regression and Neural Network Approaches to the Conformational Landscapes of Oligopeptides

Anne-Clémence Corminboeuf, Alberto Fabrizio, Michele Ceriotti, Benjamin André René Meyer, Raimon Fabregat I De Aguilar-Amat, Veronika Juraskova, Edgar Albert Engel

The application of machine learning to theoretical chemistry has made it possible to combine the accuracy of quantum chemical energetics with the thorough sampling of finite-temperature fluctuations. To reach this goal, a diverse set of methods has been pr ...

2022

Adversarial training with informed data selection

Pascal Frossard, Javier Alejandro Maroto Morales, Marcele Oliveira Kuhfuss de Mendonça

With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance. Nevertheless, state-of ...

IEEE2022

Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search

Mathieu Salzmann, Kaicheng Yu

Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware. However, recent works have empirically shown a ranking disorder between the performance of stand-alone architectures ...

IEEE COMPUTER SOC2021

Disparity Between Batches as a Signal for Early Stopping

Patrick Thiran, Mahsa Forouzesh

We propose a metric for evaluating the generalization ability of deep neural networks trained with mini-batch gradient descent. Our metric, called gradient disparity, is the l2 norm distance between the gradient vectors of two mini-batches drawn from the t ...

Springer2021

Social NCE: Contrastive Learning of Socially-aware Motion Representations

Alexandre Massoud Alahi, Yuejiang Liu

Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds. Despite promising progress, existing representations learned with neural networks sti ...

2021

Large Steps in Inverse Rendering of Geometry

Wenzel Alban Jakob, Baptiste Alexandre Marie Philippe Claude Nicolet

Inverse reconstruction from images is a central problem in many scientific and engineering disciplines. Recent progress on differentiable rendering has led to methods that can efficiently differentiate the full process of image formation with respect to mi ...

ASSOC COMPUTING MACHINERY2021

Understanding and Improving Fast Adversarial Training

Maksym Andriushchenko, Nicolas Henri Bernard Flammarion

A recent line of work focused on making adversarial training computationally efficient for deep learning models. In particular, Wong et al. (2020) showed that ℓ∞-adversarial training with fast gradient sign method (FGSM) can fail due to a phenomenon called ...

2020

Deep-learning projector for optical diffraction tomography

Michaël Unser, Thanh-An Michel Pham, Harshit Gupta, Fangshu Yang

Optical diffraction tomography is an effective tool to estimate the refractive indices of unknown objects. It proceeds by solving an ill-posed inverse problem for which the wave equation governs the scattering events. The solution has traditionally been de ...

2020

AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks

Sabine Süsstrunk, Frederike Dümbgen, Majed El Helou

The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can be expensive and time-consuming to collect. A common practical approach to attenuate overfitting i ...

IEEE2020

Page 2 sur 2