Publications related to Beyond the Pixel-Wise Loss for Topology-Aware Delineation

Related publications (28)

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Alexandre Massoud Alahi, Mohamed Ossama Ahmed Abdelfattah, Mariam Ahmed Mahmoud Hegazy Hassan

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

2024

A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods

Michaël Unser, Pakshal Narendra Bohra, Pol del Aguila Pla

We present a statistical framework to benchmark the performance of reconstruction algorithms for linear inverse problems, in particular, neural-network-based methods that require large quantities of training data. We generate synthetic signals as realizati ...

2023

Learning curves for the multi-class teacher-student perceptron

Lenka Zdeborová, Bruno Loureiro, Elisabetta Cornacchia, Rodrigo Soares Veiga

One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with a single-layer teacher-student perceptron on i.i.d. Gaussian inputs. Both Bayes-optimal (BO) ...

IOP Publishing Ltd2023

Neural Distributed Image Compression with Cross-Attention Feature Alignment

Ali Garjani

We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider ...

IEEE COMPUTER SOC2023

Bayesian Recurrent Units and the Forward-Backward Algorithm

Philip Neil Garner

Using Bayes's theorem, we derive a unit-wise recurrence as well as a backward recursion similar to the forward-backward algorithm. The resulting Bayesian recurrent units can be integrated as recurrent neural networks within deep learning frameworks, while ...

ISCA-INT SPEECH COMMUNICATION ASSOC2022

Distributed Compressed Representation of Correlated Image Sets

Vijayaraghavan Thirumalai

Vision sensor networks and video cameras find widespread usage in several applications that rely on effective representation of scenes or analysis of 3D information. These systems usually acquire multiple images of the same 3D scene from different viewpoin ...

EPFL2012

Locality defeats the curse of dimensionality in convolutional teacher-student scenarios*

Matthieu Wyart, Alessandro Favero, Francesco Cagnetta

Convolutional neural networks perform a local and translationally-invariant treatment of the data: quantifying which of these two aspects is central to their success remains a challenge. We study this problem within a teacher-student framework for kernel r ...

IOP Publishing Ltd2022

Reduced representations of complexes, signals, and multifiltrations

Celia Camille Hacker

The field of computational topology has developed many powerful tools to describe the shape of data, offering an alternative point of view from classical statistics. This results in a variety of complex structures that are not always directly amenable for ...

EPFL2022

Image Reconstruction from Compressed Linear Measurements with Side Information

Pascal Frossard, Vijayaraghavan Thirumalai

This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We consider the particular problem where one image is selected as the reference image and it is used as the side inf ...

2011

Joint reconstruction of correlated images from compressed linear measurements

Pascal Frossard, Vijayaraghavan Thirumalai

This paper proposes a joint reconstruction algorithm for compressed correlated images that are given under the form of linear measurements. We first propose a geometry based model in order to describe the correlation between visual information in pairs of ...

2010

Democratizing Machine Learning

Nirupam Gupta, Rafaël Benjamin Pinot, Alexandre David Olivier Maurer

The increasing prevalence of personal devices motivates the design of algorithms that can leverage their computing power, together with the data they generate, in order to build privacy-preserving and effective machine learning models. However, traditional ...

IEEE2022

Manifold Learning-Based Polynomial Chaos Expansions For High-Dimensional Surrogate Models

Ketson Roberto Maximiano Dos Santos

In this work we introduce a manifold learning-based method for uncertainty quantification (UQ) in systems describing complex spatiotemporal processes. Our first objective is to identify the embedding of a set of high-dimensional data representing quantitie ...

2022

Flexible Motion-Adaptive Video Coding with Redundant Expansions

Pascal Frossard, Pierre Vandergheynst, Adel Rahmoune

This paper presents a highly flexible video coding scheme (MP3D), based on the use of a redundant 3-D spatio-temporal dictionary of functions. Directionality and anisotropic scaling are key ingredients to the spatial components, that form a rich collection ...

2006

Progressive Coding of 3-D Objects Based on Overcomplete Decompositions

Pascal Frossard, Pierre Vandergheynst, Ivana Tosic

This paper presents a progressive coding scheme for 3-D objects, based on overcomplete signal expansions on the 2-D sphere. Due to increased freedom in the basis construction, redundant expansions have shown interesting approximation properties in the deco ...

2006

Automatic Content Curation of Visual Heritage

Mathieu Salzmann, Frédéric Kaplan, Nicolas Henchoz, Delphine Ribes Lemay, Lara Jacqueline Défayes, André Viegas Andrade

Digitization and preservation of large heritage induce high maintenance costs to keep up with the technical standards and ensure sustainable access. Creating impactful usage is instrumental to justify the resources for long-term preservation. The Museum fü ...

2021

Local plasticity rules can learn deep representations using self-supervised contrastive predictions

Wulfram Gerstner, Guillaume Emmanuel Fernand Bellec, Bernd Albert Illing

Learning in the brain is poorly understood and learning rules that respect biological constraints, yet yield deep hierarchical representations, are still unknown. Here, we propose a learning rule that takes inspiration from neuroscience and recent advances ...

2021

Numerical Analysis - A physics-informed multi-fidelity approach for the estimation of differential equations parameters in low-data or large-noise regimes

Alfio Quarteroni

In this paper, we propose a multi-fidelity approach for parameter estimation problems based on Physics-Informed Neural Networks (PINNs). The proposed methods apply to models expressed by linear or nonlinear differential equations, whose parameters need to ...

EUROPEAN MATHEMATICAL SOC-EMS2021

Jamming transition as a paradigm to understand the loss landscape of deep neural networks

Matthieu Wyart, Mario Geiger, Stefano Spigler, Levent Dogus Sagun

Deep learning has been immensely successful at a variety of tasks, ranging from classification to artificial intelligence. Learning corresponds to fitting training data, which is implemented by descending a very high-dimensional loss function. Understandin ...

AMER PHYSICAL SOC2019

Deep Visual Re-Identification with Confidence

Alexandre Massoud Alahi, Sven Kreiss, George Adaimi

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to better understand th ...

2019

Deep Unfolding for Communications Systems: A Survey and Some New Directions

Alexios Konstantinos Balatsoukas Stimming, Christoph Studer

Deep unfolding is a method of growing popularity that fuses iterative optimization algorithms with tools from neural networks to efficiently solve a range of tasks in machine learning, signal and image processing, and communication systems. This survey sum ...

IEEE2019