Publication

Neural Anisotropy Directions

Publications associées (32)

Crowding and the Architecture of the Visual System

Classically, vision is seen as a cascade of local, feedforward computations. This framework has been tremendously successful, inspiring a wide range of ground-breaking findings in neuroscience and computer vision. Recently, feedforward Convolutional Neural ...

EPFL2020

Model Fusion via Optimal Transport

Martin Jaggi, Sidak Pal Singh

Combining different models is a widely used paradigm in machine learning applications. While the most common approach is to form an ensemble of models and average their individual predictions, this approach is often rendered infeasible by given resource co ...

2020

Crowding reveals fundamental differences in local vs. global processing in humans and machines

Michael Herzog, Aurélien Bornet, Adrien Christophe Doerig, Oh-Hyeon Choung

Feedforward Convolutional Neural Networks (ffCNNs) have become state-of-the-art models both in computer vision and neuroscience. However, human-like performance of ffCNNs does not necessarily imply human-like computations. Previous studies have suggested t ...

2020

Learning How to Smile: Expression Video Generation With Conditional Adversarial Recurrent Nets

Wei Wang

While several research studies have focused on analyzing human behavior and, in particular, emotional signals from visual data, the problem of synthesizing face video sequences with specific attributes (e.g. age, facial expressions) received much less atte ...

2020

From Classical to Unsupervised-Deep-Learning Methods for Solving Inverse Problems in Imaging.

Harshit Gupta

In this thesis, we propose new algorithms to solve inverse problems in the context of biomedical images. Due to ill-posedness, solving these problems require some prior knowledge of the statistics of the underlying images. The traditional algorithms, in th ...

EPFL2020

Deep Semantic Segmentation Using Nir As Extra Physical Information

Sabine Süsstrunk, Siavash Arjomand Bigdeli

Deep neural networks for semantic segmentation are most often trained with RGB color images, which encode the radiation visible to the human eyes. In this paper, we study if additional physical scene information, specifically Near-Infrared (NIR) images, im ...

IEEE2019

Biologically plausible deep learning – but how far can we go with shallow networks?

Wulfram Gerstner, Johanni Michael Brea, Bernd Albert Illing

Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining s ...

2019

Hough Forest With Optimized Leaves for Global Hand Pose Estimation With Arbitrary Postures

Daniel Thalmann, Hui Liang, Jun Lee

Vision-based hand pose estimation is important in human-computer interaction. While many recent works focus on full degree-of-freedom hand pose estimation, robust estimation of global hand pose remains a challenging problem. This paper presents a novel alg ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2019

A jamming transition from under- to over-parametrization affects generalization in deep learning

Matthieu Wyart, Stefano Spigler, Levent Dogus Sagun

In this paper we first recall the recent result that in deep networks a phase transition, analogous to the jamming transition of granular media, delimits the over- and under-parametrized regimes where fitting can or cannot be achieved. The analysis leading ...

IOP PUBLISHING LTD2019

G2-VER: Geometry Guided Model Ensemble for Video-based Facial Expression Recognition

Jean-Philippe Thiran, Guillaume Marc Georges Vray, Hazim Kemal Ekenel, Tanguy Albrici

This paper addresses the problem of automatic facial expression recognition in videos, where the goal is to predict discrete emotion labels best describing the emotions expressed in short video clips. Building on a pre-trained convolutional neural network ...

IEEE2019

Graph Chatbot

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.

Connectez-vous pour utiliser Chat avec Graph Search