papers

Publications (216)

cs.LG2020

OrthoNet: Multilayer Network Data Clustering

Mireille El Gheche, Giovanni Chierchia, Pascal Frossard

Network data appears in very diverse applications, like biological, social, or sensor networks. Clustering of network nodes into categories or communities has thus become a very co…

cs.IT2008

Polynomial Filtering for Fast Convergence in Distributed Consensus

Effrosyni Kokiopoulou, Pascal Frossard

In the past few years, the problem of distributed consensus has received a lot of attention, particularly in the framework of ad hoc sensor networks. Most methods proposed in the l…

cs.LG2018

Robustness via curvature regularization, and vice versa

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Jonathan Uesato +1

State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations. One of the most effective strategies to improve robustness is adversarial traini…

cs.LG2023

MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation

Clement Vignac, Nagham Osman, Laura Toni +1

This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D arrangement of atoms. Unlike existing methods that rely on pre…

cs.LG2019

GOT: An Optimal Transport framework for Graph comparison

Hermina Petric Maretic, Mireille EL Gheche, Giovanni Chierchia +1

We present a novel framework based on optimal transport for the challenging problem of comparing graphs. Specifically, we exploit the probabilistic distribution of smooth graph sig…

cs.LG2022

On the benefits of knowledge distillation for adversarial robustness

Javier Maroto, Guillermo Ortiz-Jiménez, Pascal Frossard

Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown…

eess.SP2021

SafeAMC: Adversarial training for robust modulation recognition models

Javier Maroto, Gérôme Bovet, Pascal Frossard

In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. However, these models have been shown to be susceptib…

stat.ML2015

Multi-task additive models with shared transfer functions based on dictionary learning

Alhussein Fawzi, Mathieu Sinn, Pascal Frossard

Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer funct…

cs.MM2015

Optimal Layered Representation for Adaptive Interactive Multiview Video Streaming

Ana De Abreu, Laura Toni, Nikolaos Thomos +3

We consider an interactive multiview video streaming (IMVS) system where clients select their preferred viewpoint in a given navigation window. To provide high quality IMVS, many h…

cs.SI2015

Multiscale Event Detection in Social Media

Xiaowen Dong, Dimitrios Mavroeidis, Francesco Calabrese +1

Event detection has been one of the most important research topics in social media analysis. Most of the traditional approaches detect events based on fixed temporal and spatial re…

cs.CL2024

A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation

Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard

Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model.…

cs.CV2022

CLAD: A Contrastive Learning based Approach for Background Debiasing

Ke Wang, Harshitha Machiraju, Oh-Hyeon Choung +2

Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious…

eess.SP2019

Optimized Quantization in Distributed Graph Signal Filtering

Isabela Cunha Maia Nobre, Pascal Frossard

Distributed graph signal processing algorithms require the network nodes to communicate by exchanging messages in order to achieve a common objective. These messages have a finite…

cs.MM2012

Interactive multiview video system with non-complex navigation at the decoder

Thomas Maugey, Pascal Frossard

Multiview video with interactive and smooth view switching at the receiver is a challenging application with several issues in terms of effective use of storage and bandwidth resou…

cs.LG2025

Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein

Hugues Van Assel, Cédric Vincent-Cuaz, Nicolas Courty +3

Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR)…

cs.LG2026

Generating Directed Graphs with Dual Attention and Asymmetric Encoding

Alba Carballo-Castro, Manuel Madeira, Yiming Qin +2

Directed graphs naturally model systems with asymmetric, ordered relationships, essential to applications in biology, transportation, social networks, and visual understanding. Gen…

cs.CV2024

Hierarchical Training of Deep Neural Networks Using Early Exiting

Yamin Sepehri, Pedram Pad, Ahmet Caner Yüzügüler +2

Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the ed…

cs.MM2012

Markov Decision Process Based Energy-Efficient On-Line Scheduling for Slice-Parallel Video Decoders on Multicore Systems

Nicholas Mastronarde, Karim Kanoun, David Atienza +2

We consider the problem of energy-efficient on-line scheduling for slice-parallel video decoders on multicore systems. We assume that each of the processors are Dynamic Voltage Fre…

cs.CV2025

Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling

Adam Hazimeh, Ke Wang, Mark Collier +3

Multimedia documents such as slide presentations and posters are designed to be interactive and easy to modify. Yet, they are often distributed in a static raster format, which lim…

cs.MM2019

Visual Distortions in 360-degree Videos

Roberto G. de A. Azevedo, Neil Birkbeck, Francesca De Simone +3

Omnidirectional (or 360-degree) images and videos are emergent signals in many areas such as robotics and virtual/augmented reality. In particular, for virtual reality, they allow…

cs.IT2012

Decoding Delay Minimization in Inter-Session Network Coding

Eirina Bourtsoulatze, Nikolaos Thomos, Pascal Frossard

Intra-session network coding has been shown to offer significant gains in terms of achievable throughput and delay in settings where one source multicasts data to several clients.…

cs.NI2011

Distributed sensor failure detection in sensor networks

Tamara Tosic, Nikolaos Thomos, Pascal Frossard

We investigate the problem of distributed sensors' failure detection in networks with a small number of defective sensors, whose measurements differ significantly from neighboring…

cs.CV2021

Robustness of classifiers to universal perturbations: a geometric perspective

Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi +2

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclas…

eess.SP2020

Towards robust sensing for Autonomous Vehicles: An adversarial perspective

Apostolos Modas, Ricardo Sanchez-Matilla, Pascal Frossard +1

Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions. Fundamental building blocks of such systems are…

cs.CV2019

SparseFool: a few pixels make a big difference

Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

Deep Neural Networks have achieved extraordinary results on image classification tasks, but have been shown to be vulnerable to attacks with carefully crafted perturbations of the…

cs.LG2023

DiGress: Discrete Denoising diffusion for graph generation

Clement Vignac, Igor Krawczuk, Antoine Siraudin +3

This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. Our model utilizes a discrete diffusion process…

cs.LG2026

RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities

Vasiliki Rizou, Pascal Frossard, Dorina Thanou

To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and exploit all cross-modal interacti…

cs.CL2023

TransFool: An Adversarial Attack against Neural Machine Translation Models

Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard

Deep neural networks have been shown to be vulnerable to small perturbations of their inputs, known as adversarial attacks. In this paper, we investigate the vulnerability of Neura…

cs.CL2023

Targeted Adversarial Attacks against Neural Machine Translation

Sahar Sadrizadeh, AmirHossein Dabiri Aghdam, Ljiljana Dolamic +1

Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as…

cs.NI2011

Approximate Decoding Approaches for Network Coded Correlated Data

Hyunggon Park, Nikolaos Thomos, Pascal Frossard

This paper considers a framework where data from correlated sources are transmitted with help of network coding in ad-hoc network topologies. The correlated data are encoded indepe…

cs.LG2011

Clustering with Multi-Layer Graphs: A Spectral Perspective

Xiaowen Dong, Pascal Frossard, Pierre Vandergheynst +1

Observational data usually comes with a multimodal nature, which means that it can be naturally represented by a multi-layer graph whose layers share the same set of vertices (user…

cs.CV2011

Correlation Estimation from Compressed Images

Vijayaraghavan Thirumalai, Pascal Frossard

This paper addresses the problem of correlation estimation in sets of compressed images. We consider a framework where images are represented under the form of linear measurements…

cs.LG2025

Task Addition and Weight Disentanglement in Closed-Vocabulary Models

Adam Hazimeh, Alessandro Favero, Pascal Frossard

Task arithmetic has recently emerged as a promising method for editing pre-trained \textit{open-vocabulary} models, offering a cost-effective alternative to standard multi-task fin…

stat.ML2025

How Compositional Generalization and Creativity Improve as Diffusion Models are Trained

Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta +2

Natural data is often organized as a hierarchical composition of features. How many samples do generative models need in order to learn the composition rules, so as to produce a co…

cs.LG2020

Neural Anisotropy Directions

Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli +1

In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers. To that end, we start by focusing on a very simple problem, i.e., c…

cs.LG2024

Deep End-to-End Survival Analysis with Temporal Consistency

Mariana Vargas Vieyra, Pascal Frossard

In this study, we present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. Our approach draws inspiration from Reinforcement Learni…

cs.IT2014

Adaptive Prioritized Random Linear Coding and Scheduling for Layered Data Delivery from Multiple Servers

Nikolaos Thomos, Eymen Kurdoglu, Pascal Frossard +1

In this paper, we deal with the problem of jointly determining the optimal coding strategy and the scheduling decisions when receivers obtain layered data from multiple servers. Th…

cs.CV2015

Manitest: Are classifiers really invariant?

Alhussein Fawzi, Pascal Frossard

Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks. Nevertheless, it is unclear to which extent state-o…

cs.DM2013

The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains

David I Shuman, Sunil K. Narang, Pascal Frossard +2

In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs. The emerging field…

cs.LG2019

Stochastic Gradient Descent for Spectral Embedding with Implicit Orthogonality Constraint

Mireille El Gheche, Giovanni Chierchia, Pascal Frossard

In this paper, we propose a scalable algorithm for spectral embedding. The latter is a standard tool for graph clustering. However, its computational bottleneck is the eigendecompo…

cs.LG2021

What can linearized neural networks actually say about generalization?

Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK onl…

cs.SI2020

On the choice of graph neural network architectures

Clément Vignac, Guillermo Ortiz-Jiménez, Pascal Frossard

Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals. With the developm…

cs.LG2026

Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability

Mathieu Cyrille Simon, Pascal Frossard, Christophe De Vleeschouwer

This paper explores unsupervised disentangled representation learning from a functional perspective. We define latent concepts as factors that influence observations through locall…

cs.LG2025

Backdoor Unlearning by Linear Task Decomposition

Amel Abdelraheem, Alessandro Favero, Gerome Bovet +1

Foundation models have revolutionized computer vision by enabling broad generalization across diverse tasks. Yet, they remain highly susceptible to adversarial perturbations and ta…

cs.LG2023

Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models

Nikolaos Dimitriadis, Pascal Frossard, François Fleuret

In Multi-Task Learning (MTL), tasks may compete and limit the performance achieved on each other, rather than guiding the optimization to a solution, superior to all its single-tas…

cs.LG2022

A Structured Dictionary Perspective on Implicit Neural Representations

Gizem Yüce, Guillermo Ortiz-Jiménez, Beril Besbinar +1

Implicit neural representations (INRs) have recently emerged as a promising alternative to classical discretized representations of signals. Nevertheless, despite their practical s…

cs.DS2009

A note on the data-driven capacity of P2P networks

Jacob Chakareski, Pascal Frossard, Hervé Kerivin +2

We consider two capacity problems in P2P networks. In the first one, the nodes have an infinite amount of data to send and the goal is to optimally allocate their uplink bandwidths…

cs.LG2021

FGOT: Graph Distances based on Filters and Optimal Transport

Hermina Petric Maretic, Mireille El Gheche, Giovanni Chierchia +1

Graph comparison deals with identifying similarities and dissimilarities between graphs. A major obstacle is the unknown alignment of graphs, as well as the lack of accurate and in…

cs.CV2012

Learning Smooth Pattern Transformation Manifolds

Elif Vural, Pascal Frossard

Manifold models provide low-dimensional representations that are useful for processing and analyzing data in a transformation-invariant way. In this paper, we study the problem of…

cs.IT2024

Subgraph Matching via Partial Optimal Transport

Wen-Xin Pan, Isabel Haasler, Pascal Frossard

In this work, we propose a novel approach for subgraph matching, the problem of finding a given query graph in a large source graph, based on the fused Gromov-Wasserstein distance.…

cs.CL2020

QUACKIE: A NLP Classification Task With Ground Truth Explanations

Yves Rychener, Xavier Renard, Djamé Seddah +2

NLP Interpretability aims to increase trust in model predictions. This makes evaluating interpretability approaches a pressing issue. There are multiple datasets for evaluating NLP…

cs.LG2023

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

Guillermo Ortiz-Jimenez, Alessandro Favero, Pascal Frossard

Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different ta…

cs.IT2019

Graph Transform Optimization with Application to Image Compression

Giulia Fracastoro, Dorina Thanou, Pascal Frossard

In this paper, we propose a new graph-based transform and illustrate its potential application to signal compression. Our approach relies on the careful design of a graph that opti…

cs.NI2012

Thresholding-based reconstruction of compressed correlated signals

Alhussein Fawzi, Tamara Tosic, Pascal Frossard

We consider the problem of recovering a set of correlated signals (e.g., images from different viewpoints) from a few linear measurements per signal. We assume that each sensor in…

cs.CV2021

Privacy-Preserving Image Acquisition Using Trainable Optical Kernel

Yamin Sepehri, Pedram Pad, Pascal Frossard +1

Preserving privacy is a growing concern in our society where sensors and cameras are ubiquitous. In this work, for the first time, we propose a trainable image acquisition method t…

cs.CV2009

Graph-based classification of multiple observation sets

Effrosyni Kokiopoulou, Pascal Frossard

We consider the problem of classification of an object given multiple observations that possibly include different transformations. The possible transformations of the object gener…

cs.LG2026

Fixed-Point Masked Generative Modeling

Andrea Miele, Yiming Qin, Alba Carballo-Castro +2

Masked Generative Models (MGMs) enable parallel decoding and achieve strong performance across modalities, but require full-sequence bidirectional transformers at every step, makin…

cs.CV2020

GeoDA: a geometric framework for black-box adversarial attacks

Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard +1

Adversarial examples are known as carefully perturbed images fooling image classifiers. We propose a geometric framework to generate adversarial examples in one of the most challen…

cs.CL2022

On the Granularity of Explanations in Model Agnostic NLP Interpretability

Yves Rychener, Xavier Renard, Djamé Seddah +2

Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this pa…

cs.CV2014

Dictionary learning for fast classification based on soft-thresholding

Alhussein Fawzi, Mike Davies, Pascal Frossard

Classifiers based on sparse representations have recently been shown to provide excellent results in many visual recognition and classification tasks. However, the high cost of com…

cs.LG2023

Catastrophic overfitting can be induced with discriminative non-robust features

Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal +5

Adversarial training (AT) is the de facto method for building robust neural networks, but it can be computationally expensive. To mitigate this, fast single-step attacks can be use…

cs.LG2021

Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs

Semin Kwak, Nikolas Geroliminis, Pascal Frossard

Multivariate time series forecasting poses challenges as the variables are intertwined in time and space, like in the case of traffic signals. Defining signals on graphs relaxes su…

stat.CO2013

Tangent space estimation for smooth embeddings of Riemannian manifolds

Hemant Tyagi, Elif Vural, Pascal Frossard

Numerous dimensionality reduction problems in data analysis involve the recovery of low-dimensional models or the learning of manifolds underlying sets of data. Many manifold learn…

cs.LG2022

Data augmentation with mixtures of max-entropy transformations for filling-level classification

Apostolos Modas, Andrea Cavallaro, Pascal Frossard

We address the problem of distribution shifts in test-time data with a principled data augmentation scheme for the task of content-level classification. In such a task, properties…

cs.MM2013

Graph-based representation for multiview image coding

Thomas Maugey, Antonio Ortega, Pascal Frossard

In this paper, we propose a new representation for multiview image sets. Our approach relies on graphs to describe geometry information in a compact and controllable way. The links…

cs.LG2021

Message Passing in Graph Convolution Networks via Adaptive Filter Banks

Xing Gao, Wenrui Dai, Chenglin Li +3

Graph convolution networks, like message passing graph convolution networks (MPGCNs), have been a powerful tool in representation learning of networked data. However, when data is…

stat.ML2019

Forward-Backward Splitting for Optimal Transport based Problems

Guillermo Ortiz-Jimenez, Mireille El Gheche, Effrosyni Simou +2

Optimal transport aims to estimate a transportation plan that minimizes a displacement cost. This is realized by optimizing the scalar product between the sought plan and the given…

cs.LG2016

Robustness of classifiers: from adversarial to random noise

Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

Several recent works have shown that state-of-the-art classifiers are vulnerable to worst-case (i.e., adversarial) perturbations of the datapoints. On the other hand, it has been e…

cs.LG2019

Learning graphs from data: A signal representation perspective

Xiaowen Dong, Dorina Thanou, Michael Rabbat +1

The construction of a meaningful graph topology plays a crucial role in the effective representation, processing, analysis and visualization of structured data. When a natural choi…

cs.CV2017

Classification regions of deep neural networks

Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard +1

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions cr…

cs.CV2017

Graph-based Isometry Invariant Representation Learning

Renata Khasanova, Pascal Frossard

Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for im…

stat.ML2026

DiPhon: Diffusion on Graphons for Scalable Graph Generation

Sergio Rozada, Yiming Qin, Manuel Madeira +2

Diffusion models represent a leading paradigm for graph generation, with notable impact in domains such as molecular design. Yet, scaling these models to large graphs remains an op…

cs.IT2015

Prioritized Random MAC Optimization via Graph-based Analysis

Laura Toni, Pascal Frossard

Motivated by the analogy between successive interference cancellation and iterative belief-propagation on erasure channels, irregular repetition slotted ALOHA (IRSA) strategies hav…

cs.CV2018

Isometric Transformation Invariant Graph-based Deep Neural Network

Renata Khasanova, Pascal Frossard

Learning transformation invariant representations of visual data is an important problem in computer vision. Deep convolutional networks have demonstrated remarkable results for im…

cs.CV2020

Multi-view shape estimation of transparent containers

Alessio Xompero, Ricardo Sanchez-Matilla, Apostolos Modas +2

The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions.…

cs.IT2018

Supervised Linear Regression for Graph Learning from Graph Signals

Arun Venkitaraman, Hermina Petric Maretic, Saikat Chatterjee +1

We propose a supervised learning approach for predicting an underlying graph from a set of graph signals. Our approach is based on linear regression. In the linear regression model…

cs.LG2026

Geodesics of Dynamic Graphs for Regime Change Detection

William Cappelletti, Étienne Voutaz, Pascal Frossard

Traditional change point detection in dynamic networks assumes abrupt transitions between stationary states, overlooking scenarios of continuous evolution which arise in most real-…

cs.IR2016

Multi-modal image retrieval with random walk on multi-layer graphs

Renata Khasanova, Xiaowen Dong, Pascal Frossard

The analysis of large collections of image data is still a challenging problem due to the difficulty of capturing the true concepts in visual data. The similarity between images co…

cs.CV2021

Bio-inspired Robustness: A Review

Harshitha Machiraju, Oh-Hyeon Choung, Pascal Frossard +1

Deep convolutional neural networks (DCNNs) have revolutionized computer vision and are often advocated as good models of the human visual system. However, there are currently many…

cs.MM2012

Joint Reconstruction of Multi-view Compressed Images

Vijayaraghavan Thirumalai, Pascal Frossard

The distributed representation of correlated multi-view images is an important problem that arise in vision sensor networks. This paper concentrates on the joint reconstruction pro…

cs.MM2014

Optimized Packet Scheduling in Multiview Video Navigation Systems

Laura Toni, Thomas Maugey, Pascal Frossard

In multiview video systems, multiple cameras generally acquire the same scene from different perspectives, such that users have the possibility to select their preferred viewpoint.…

cs.CL2023

A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models

Sahar Sadrizadeh, Clément Barbier, Ljiljana Dolamic +1

In this paper, we propose an optimization-based adversarial attack against Neural Machine Translation (NMT) models. First, we propose an optimization problem to generate adversaria…

cs.DM2018

Convolutional neural networks on irregular domains based on approximate vertex-domain translations

Bastien Pasdeloup, Vincent Gripon, Jean-Charles Vialatte +2

We propose a generalization of convolutional neural networks (CNNs) to irregular domains, through the use of a translation operator on a graph structure. In regular settings such a…

cs.LG2026

ODySSeI: An Open-Source End-to-End Framework for Automated Detection, Segmentation, and Severity Estimation of Lesions in Invasive Coronary Angiography Images

Anand Choudhary, Xiaowu Sun, Thabo Mahendiran +8

Invasive Coronary Angiography (ICA) is the clinical gold standard for the assessment of coronary artery disease. However, its interpretation remains subjective and prone to intra-…

cs.LG2026

DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Models

Yiming Qin, Kai Yi, Miruna Cretu +3

Designing small molecule ligands that bind with high affinity to specific protein pockets is a fundamental goal in drug discovery, as small molecules constitute a major fraction of…

cs.CV2024

IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection

Junbo Yin, Jianbing Shen, Runnan Chen +4

Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typicall…

cs.GR2025

A Fast Volumetric Capture and Reconstruction Pipeline for Dynamic Point Clouds and Gaussian Splats

Athanasios Charisoudis, Simone Croci, Lam Kit Yung +2

We present a fast and efficient volumetric capture and reconstruction system that processes either RGB-D or RGB-only input to generate 3D representations in the form of point cloud…

cs.LG2016

Analysis of classifiers' robustness to adversarial perturbations

Alhussein Fawzi, Omar Fawzi, Pascal Frossard

The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep networks, namely their instability to adversarial perturbations (Szegedy et. al., 2014). W…

cs.LG2020

FiGLearn: Filter and Graph Learning using Optimal Transport

Matthias Minder, Zahra Farsijani, Dhruti Shah +2

In many applications, a dataset can be considered as a set of observed signals that live on an unknown underlying graph structure. Some of these signals may be seen as white noise…

cs.IT2012

Intermediate Performance Analysis of Growth Codes

Nikolaos Thomos, Rethnakaran Pulikkoonattu, Pascal Frossard

Growth codes are a subclass of Rateless codes that have found interesting applications in data dissemination problems. Compared to other Rateless and conventional channel codes, Gr…

cs.LG2021

node2coords: Graph Representation Learning with Wasserstein Barycenters

Effrosyni Simou, Dorina Thanou, Pascal Frossard

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods do not learn rep…

cs.LG2023

Online Network Source Optimization with Graph-Kernel MAB

Laura Toni, Pascal Frossard

We propose Grab-UCB, a graph-kernel multi-arms bandit algorithm to learn online the optimal source placement in large scale networks, such that the reward obtained from a priori un…

cs.NI2013

Distributed Rate Allocation in Inter-Session Network Coding

Eirina Bourtsoulatze, Nikolaos Thomos, Pascal Frossard

In this work, we propose a distributed rate allocation algorithm that minimizes the average decoding delay for multimedia clients in inter-session network coding systems. We consid…

cs.MM2021

Multi-feature 360 Video Quality Estimation

Roberto G. de A. Azevedo, Neil Birkbeck, Ivan Janatra +2

We propose a new method for the visual quality assessment of 360-degree (omnidirectional) videos. The proposed method is based on computing multiple spatio-temporal objective quali…

cs.MM2014

Optimized Adaptive Streaming Representations based on System Dynamics

Laura Toni, Ramon Aparicio-Pardo, Karine Pires +3

Adaptive streaming addresses the increasing and heterogenous demand of multimedia content over the Internet by offering several encoded versions for each video sequence. Each versi…

cs.MM2013

Multi-View Video Packet Scheduling

Laura Toni, Thomas Maugey, Pascal Frossard

In multiview applications, multiple cameras acquire the same scene from different viewpoints and generally produce correlated video streams. This results in large amounts of highly…

cs.LG2022

Maximum Likelihood Distillation for Robust Modulation Classification

Javier Maroto, Gérôme Bovet, Pascal Frossard

Deep Neural Networks are being extensively used in communication systems and Automatic Modulation Classification (AMC) in particular. However, they are very susceptible to small ad…

cs.CV2021

Self-Supervision by Prediction for Object Discovery in Videos

Beril Besbinar, Pascal Frossard

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about d…

cs.LG2026

Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs

Antonis Vasileiou, Juan Cervino, Pascal Frossard +7

Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine lea…

stat.ML2018

Kernel Regression for Graph Signal Prediction in Presence of Sparse Noise

Arun Venkitaraman, Pascal Frossard, Saikat Chatterjee

In presence of sparse noise we propose kernel regression for predicting output vectors which are smooth over a given graph. Sparse noise models the training outputs being corrupted…