Publication

Safety-Compliant Generative Adversarial Networks for Human Trajectory Forecasting

Publications associées (31)

Adversarial Robustness by Design Through Analog Computing And Synthetic Gradients

Florent Gérard Krzakala, Julien Marcel Daniel Emmanuel Launay, Ruben Elie Ohana

We propose a new defense mechanism against adversarial at-tacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and black-box settings. This hardware co-processor performs a nonlinear fixed ...

IEEE2022

Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting

Alexandre Massoud Alahi, Yuejiang Liu, Parth Ashit Kothari, Danya Li

Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for efficiently adapting p ...

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

Towards Empathetic Open-Domain Chatbots

Yubo Xie

The research community of dialog generation has been interested in incorporating emotional information into the design of open-domain dialog systems ever since neural networks (sequence-to-sequence models in particular) were adopted for modeling dialogs. T ...

EPFL2022

Controllability and Interpretability in Affective Speech Synthesis

Bastian Schnell

Thanks to Deep Learning Text-To-Speech (TTS) has achieved high audio quality with large databases. But at the same time the complex models lost any ability to control or interpret the generation process. For the big challenge of affective TTS it is infeasi ...

EPFL2022

Downscaling of Historical Wind Fields over Switzerland Using Generative Adversarial Networks

Anthony Christopher Davison, Ophélia Mireille Anna Miralles

Near-surface wind is difficult to estimate using global numerical weather and climate models, because airflow is strongly modified by underlying topography, especially that of a country such as Switzerland. In this article, we use a statistical approach ba ...

2022

Robust Binary Models by Pruning Randomly-initialized Networks

Sabine Süsstrunk, Mathieu Salzmann, Chen Liu, Ziqi Zhao

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks. Unlike adversar ...

2022

MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations

Demetri Psaltis, Joowon Lim

Maxwell's equations govern light propagation and its interaction with matter. Therefore, the solution of Maxwell's equations using computational electromagnetic simulations plays a critical role in understanding light-matter interaction and designing optic ...

AIP Publishing2022

Theory of Deep Learning: Neural Tangent Kernel and Beyond

Arthur Ulysse Jacot-Guillarmod

In the recent years, Deep Neural Networks (DNNs) have managed to succeed at tasks that previously appeared impossible, such as human-level object recognition, text synthesis, translation, playing games and many more. In spite of these major achievements, o ...

EPFL2022

Face Reconstruction Fromdeep Facial Embeddings Using A Convolutional Neural Network

Sébastien Marcel, Hatef Otroshi Shahreza

State-of-the-art (SOTA) face recognition systems generally use deep convolutional neural networks (CNNs) to extract deep features, called embeddings, from face images. The face embeddings are stored in the system's database and are used for recognition of ...

IEEE2022