Search Results for author: Pascal Frossard

Found 125 papers, 50 papers with code

Localizing Task Information for Improved Model Merging and Compression

1 code implementation13 May 2024 Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez, François Fleuret, Pascal Frossard

For this reason, we propose Consensus Merging, an algorithm that eliminates such weights and improves the general performance of existing model merging approaches.

PUMA: margin-based data pruning

no code implementations10 May 2024 Javier Maroto, Pascal Frossard

We thus propose PUMA, a new data pruning strategy that computes the margin using DeepFool, and prunes the training samples of highest margin without hurting performance by jointly adjusting the training attack norm on the samples of lowest margin.

Sparse Training of Discrete Diffusion Models for Graph Generation

1 code implementation3 Nov 2023 Yiming Qin, Clement Vignac, Pascal Frossard

Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs.

Denoising Graph Generation

Causal Temporal Regime Structure Learning

no code implementations2 Nov 2023 Abdellah Rahmani, Pascal Frossard

We address the challenge of structure learning from multivariate time series that are characterized by a sequence of different, unknown regimes.

Causal Discovery Time Series

Tertiary Lymphoid Structures Generation through Graph-based Diffusion

no code implementations10 Oct 2023 Manuel Madeira, Dorina Thanou, Pascal Frossard

In particular, we show that the adopted graph diffusion model is able to accurately learn the distribution of cells in terms of their tertiary lymphoid structures (TLS) content, a well-established biomarker for evaluating the cancer progression in oncology research.

Data Augmentation

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels

no code implementations10 Oct 2023 Ke Wang, Guillermo Ortiz-Jimenez, Rodolphe Jenatton, Mark Collier, Efi Kokiopoulou, Pascal Frossard

Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models.

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

no code implementations29 Aug 2023 Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard

To evaluate the robustness of NMT models to our attack, we propose enhancements to existing black-box word-replacement-based attacks by incorporating output translations of the target NMT model and the output logits of a classifier within the attack process.

Adversarial Attack Machine Translation +2

Online Network Source Optimization with Graph-Kernel MAB

no code implementations7 Jul 2023 Laura Toni, Pascal Frossard

To achieve sample efficiency, we describe the network processes with an adaptive graph dictionary model, which typically leads to sparse spectral representations.

DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

1 code implementation5 Jul 2023 Adam Ivankay, Mattia Rigotti, Pascal Frossard

This results in our DomainAdaptiveAREstimator (DARE) attribution robustness estimator, allowing us to properly characterize the domain-specific robustness of faithful explanations.

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

no code implementations14 Jun 2023 Sahar Sadrizadeh, Clément Barbier, Ljiljana Dolamic, Pascal Frossard

First, we propose an optimization problem to generate adversarial examples that are semantically similar to the original sentences but destroy the translation generated by the target NMT model.

Adversarial Attack Machine Translation +4

Flexible Channel Dimensions for Differentiable Architecture Search

no code implementations13 Jun 2023 Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard

Finding optimal channel dimensions (i. e., the number of filters in DNN layers) is essential to design DNNs that perform well under computational resource constraints.

Neural Architecture Search

Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions

1 code implementation12 Jun 2023 Harshitha Machiraju, Michael H. Herzog, Pascal Frossard

In response, researchers have developed image corruption datasets to evaluate the performance of deep neural networks in handling such corruptions.

Classification Robust classification

Bures-Wasserstein Means of Graphs

no code implementations31 May 2023 Isabel Haasler, Pascal Frossard

Finding the mean of sampled data is a fundamental task in machine learning and statistics.

Graph Similarity Node Classification

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

1 code implementation NeurIPS 2023 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 tasks, the model's performance can be improved on these tasks, while negating them leads to task forgetting.

Disentanglement Image Classification

SequeL: A Continual Learning Library in PyTorch and JAX

1 code implementation21 Apr 2023 Nikolaos Dimitriadis, Francois Fleuret, Pascal Frossard

Continual Learning is an important and challenging problem in machine learning, where models must adapt to a continuous stream of new data without forgetting previously acquired knowledge.

Continual Learning

Knowledge-Distilled Graph Neural Networks for Personalized Epileptic Seizure Detection

no code implementations3 Apr 2023 Qinyue Zheng, Arun Venkitaraman, Simona Petravic, Pascal Frossard

We consider two cases (a) when a single student is learnt for all the patients using preselected channels; and (b) when personalized students are learnt for every individual patient, with personalized channel selection using a Gumbelsoftmax approach.

EEG Knowledge Distillation +1

Hierarchical Training of Deep Neural Networks Using Early Exiting

no code implementations4 Mar 2023 Yamin Sepehri, Pedram Pad, Ahmet Caner Yüzügüler, Pascal Frossard, L. Andrea Dunbar

In this study, a novel hierarchical training method for deep neural networks is proposed that uses early exits in a divided architecture between edge and cloud workers to reduce the communication cost, training runtime and privacy concerns.

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

1 code implementation17 Feb 2023 Clement Vignac, Nagham Osman, Laura Toni, Pascal Frossard

This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D arrangement of atoms.


TransFool: An Adversarial Attack against Neural Machine Translation Models

1 code implementation2 Feb 2023 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.

Adversarial Attack Language Modelling +5

Adversarial training with informed data selection

no code implementations7 Jan 2023 Marcele O. K. Mendonça, Javier Maroto, Pascal Frossard, Paulo S. R. Diniz

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.

Estimating the Adversarial Robustness of Attributions in Text with Transformers

no code implementations18 Dec 2022 Adam Ivankay, Mattia Rigotti, Ivan Girardi, Chiara Marchiori, Pascal Frossard

Finally, with experiments on several text classification architectures, we show that TEA consistently outperforms current state-of-the-art AR estimators, yielding perturbations that alter explanations to a greater extent while being more fluent and less perceptible.

Adversarial Robustness text-classification +2

SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud

1 code implementation6 Dec 2022 Yan Wang, Junbo Yin, Wei Li, Pascal Frossard, Ruigang Yang, Jianbing Shen

However, these UDA solutions just yield unsatisfactory 3D detection results when there is a severe domain shift, e. g., from Waymo (64-beam) to nuScenes (32-beam).

3D Object Detection Autonomous Driving +5

A Meta-GNN approach to personalized seizure detection and classification

no code implementations1 Nov 2022 Abdellah Rahmani, Arun Venkitaraman, Pascal Frossard

In this paper, we propose a personalized seizure detection and classification framework that quickly adapts to a specific patient from limited seizure samples.

Meta-Learning Seizure Detection

Maximum Likelihood Distillation for Robust Modulation Classification

no code implementations1 Nov 2022 Javier Maroto, Gérôme Bovet, Pascal Frossard

Deep Neural Networks are being extensively used in communication systems and Automatic Modulation Classification (AMC) in particular.

Classification Knowledge Distillation

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

1 code implementation18 Oct 2022 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-task trained counterparts.

Image Classification Multi-Task Learning +1

Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design

1 code implementation11 Oct 2022 Ilia Igashov, Hannes Stärk, Clément Vignac, Victor Garcia Satorras, Pascal Frossard, Max Welling, Michael Bronstein, Bruno Correia

Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments.

Drug Discovery valid

CLAD: A Contrastive Learning based Approach for Background Debiasing

1 code implementation6 Oct 2022 Ke Wang, Harshitha Machiraju, Oh-Hyeon Choung, Michael Herzog, Pascal Frossard

Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification.

Contrastive Learning Image Classification

DiGress: Discrete Denoising diffusion for graph generation

2 code implementations29 Sep 2022 Clement Vignac, Igor Krawczuk, Antoine Siraudin, Bohan Wang, Volkan Cevher, Pascal Frossard

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

Denoising Edge Classification +1

Catastrophic overfitting can be induced with discriminative non-robust features

1 code implementation16 Jun 2022 Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal, Adel Bibi, Puneet K. Dokania, Pascal Frossard, Gregory Rogéz, Philip H. S. Torr

Through extensive experiments we analyze this novel phenomenon and discover that the presence of these easy features induces a learning shortcut that leads to CO. Our findings provide new insights into the mechanisms of CO and improve our understanding of the dynamics of AT.

Robust classification

Fooling Explanations in Text Classifiers

no code implementations ICLR 2022 Adam Ivankay, Ivan Girardi, Chiara Marchiori, Pascal Frossard

TEF can significantly decrease the correlation between unchanged and perturbed input attributions, which shows that all models and explanation methods are susceptible to TEF perturbations.

text-classification Text Classification

Hierarchical Spherical CNNs with Lifting-based Adaptive Wavelets for Pooling and Unpooling

no code implementations31 May 2022 Mingxing Xu, Chenglin Li, Wenrui Dai, Siheng Chen, Junni Zou, Pascal Frossard, Hongkai Xiong

Specifically, adaptive spherical wavelets are learned with a lifting structure that consists of trainable lifting operators (i. e., update and predict operators).

Empirical Advocacy of Bio-inspired Models for Robust Image Recognition

1 code implementation18 May 2022 Harshitha Machiraju, Oh-Hyeon Choung, Michael H. Herzog, Pascal Frossard

There are continuous attempts to use features of the human visual system to improve the robustness of neural networks to data perturbations.

Data Augmentation

Scale-out Systolic Arrays

1 code implementation22 Mar 2022 Ahmet Caner Yüzügüler, Canberk Sönmez, Mario Drumond, Yunho Oh, Babak Falsafi, Pascal Frossard

In this work, we study three key pillars in multi-pod systolic array designs, namely array granularity, interconnect, and tiling.

On the benefits of knowledge distillation for adversarial robustness

no code implementations14 Mar 2022 Javier Maroto, Guillermo Ortiz-Jiménez, Pascal Frossard

To that end, we present Adversarial Knowledge Distillation (AKD), a new framework to improve a model's robust performance, consisting on adversarially training a student on a mixture of the original labels and the teacher outputs.

Adversarial Robustness Knowledge Distillation

Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers

1 code implementation11 Mar 2022 Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard

Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples.

Adversarial Attack Sentence

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

no code implementations8 Mar 2022 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.

Data Augmentation Transfer Learning

PRIME: A few primitives can boost robustness to common corruptions

1 code implementation27 Dec 2021 Apostolos Modas, Rahul Rade, Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data.

Computational Efficiency Data Augmentation +2

Distributed Graph Learning with Smooth Data Priors

no code implementations11 Dec 2021 Isabela Cunha Maia Nobre, Mireille El Gheche, Pascal Frossard

We propose here a novel distributed graph learning algorithm, which permits to infer a graph from signal observations on the nodes under the assumption that the data is smooth on the target graph.

Distributed Optimization Graph Learning +1

A Structured Dictionary Perspective on Implicit Neural Representations

1 code implementation CVPR 2022 Gizem Yüce, Guillermo Ortiz-Jiménez, Beril Besbinar, Pascal Frossard

Leveraging results from harmonic analysis and deep learning theory, we show that most INR families are analogous to structured signal dictionaries whose atoms are integer harmonics of the set of initial mapping frequencies.

Dictionary Learning Inductive Bias +2

Top-N: Equivariant set and graph generation without exchangeability

1 code implementation ICLR 2022 Clement Vignac, Pascal Frossard

This work addresses one-shot set and graph generation, and, more specifically, the parametrization of probabilistic decoders that map a vector-shaped prior to a distribution over sets or graphs.

Drug Discovery Generative Adversarial Network +4

Graph Convolutional Networks via Adaptive Filter Banks

no code implementations29 Sep 2021 Xing Gao, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong, Pascal Frossard

Graph convolutional networks have been a powerful tool in representation learning of networked data.

Representation Learning

An evaluation of quality and robustness of smoothed explanations

no code implementations29 Sep 2021 Ahmad Ajalloeian, Seyed-Mohsen Moosavi-Dezfooli, Michalis Vlachos, Pascal Frossard

However, a combination of additive and non-additive attacks can still manipulate these explanations, which reveals shortcomings in their robustness properties.

FGOT: Graph Distances based on Filters and Optimal Transport

2 code implementations9 Sep 2021 Hermina Petric Maretic, Mireille El Gheche, Giovanni Chierchia, Pascal Frossard

We tackle the problem of graph alignment by computing graph permutations that minimise our new filter distances, which implicitly solves the graph comparison problem.

Graph Neural Networks With Lifting-based Adaptive Graph Wavelets

no code implementations3 Aug 2021 Mingxing Xu, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong, Pascal Frossard

To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information.

Graph Representation Learning

Privacy-Preserving Image Acquisition Using Trainable Optical Kernel

no code implementations28 Jun 2021 Yamin Sepehri, Pedram Pad, Pascal Frossard, L. Andrea Dunbar

Also, in contrast with the previous optical privacy-preserving methods that cannot be trained, our method is data-driven and optimized for the specific application at hand.

Attribute Privacy Preserving

Message Passing in Graph Convolution Networks via Adaptive Filter Banks

no code implementations18 Jun 2021 Xing Gao, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong, Pascal Frossard

Furthermore, each filter in the spectral domain corresponds to a message passing scheme, and diverse schemes are implemented via the filter bank.

Graph Classification Representation Learning

What can linearized neural networks actually say about generalization?

1 code implementation NeurIPS 2021 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 only provides a rough first-order approximation.

SafeAMC: Adversarial training for robust modulation recognition models

no code implementations28 May 2021 Javier Maroto, Gérôme Bovet, Pascal Frossard

We propose to use adversarial training, which consists of fine-tuning the model with adversarial perturbations, to increase the robustness of automatic modulation recognition (AMC) models.

Automatic Modulation Recognition

A neural anisotropic view of underspecification in deep learning

no code implementations29 Apr 2021 Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

In this work, we propose to study this problem from a geometric perspective with the aim to understand two key characteristics of neural network solutions in underspecified settings: how is the geometry of the learned function related to the data representation?

Fairness Inductive Bias

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

2 code implementations27 Apr 2021 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.

Ranked #7 on Traffic Prediction on PEMS-BAY (RMSE metric)

Multivariate Time Series Forecasting Time Series +1

Multilayer Graph Clustering with Optimized Node Embedding

no code implementations30 Mar 2021 Mireille El Gheche, Pascal Frossard

To do so, we propose to learn a clustering-friendly embedding of the graph nodes by solving an optimization problem that involves a fidelity term to the layers of a given multilayer graph, and a regularization on the (single-layer) graph induced by the embedding.

Clustering Graph Clustering

On the benefits of robust models in modulation recognition

no code implementations27 Mar 2021 Javier Maroto, Gérôme Bovet, Pascal Frossard

When analyzing these vulnerable models we found that adversarial perturbations do not shift the symbols towards the nearest classes in constellation space.

Image Classification

Bio-inspired Robustness: A Review

no code implementations16 Mar 2021 Harshitha Machiraju, Oh-Hyeon Choung, Pascal Frossard, Michael. H Herzog

Many studies have tried to add features of the human visual system to DCNNs to make them robust against adversarial attacks.

Self-Supervision by Prediction for Object Discovery in Videos

no code implementations9 Mar 2021 Beril Besbinar, Pascal Frossard

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data.

Inductive Bias Object +4

On the Granularity of Explanations in Model Agnostic NLP Interpretability

1 code implementation24 Dec 2020 Yves Rychener, Xavier Renard, Djamé Seddah, Pascal Frossard, Marcin Detyniecki

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.

Multilayer Clustered Graph Learning

no code implementations29 Oct 2020 Mireille El Gheche, Pascal Frossard

In this paper, we aim at analyzing multilayer graphs by properly combining the information provided by individual layers, while preserving the specific structure that allows us to eventually identify communities or clusters that are crucial in the analysis of graph data.

Clustering Graph Learning

FiGLearn: Filter and Graph Learning using Optimal Transport

no code implementations29 Oct 2020 Matthias Minder, Zahra Farsijani, Dhruti Shah, Mireille El Gheche, Pascal Frossard

We cast a new optimisation problem that minimises the Wasserstein distance between the distribution of the signal observations and the filtered signal distribution model.

Graph Learning

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness

no code implementations19 Oct 2020 Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

In this article, we provide an in-depth review of the field of adversarial robustness in deep learning, and give a self-contained introduction to its main notions.

Adversarial Robustness

FAR: A General Framework for Attributional Robustness

no code implementations14 Oct 2020 Adam Ivankay, Ivan Girardi, Chiara Marchiori, Pascal Frossard

Therefore, we define a novel generic framework for attributional robustness (FAR) as general problem formulation for training models with robust attributions.

Modurec: Recommender Systems with Feature and Time Modulation

1 code implementation13 Oct 2020 Javier Maroto, Clément Vignac, Pascal Frossard

Current state of the art algorithms for recommender systems are mainly based on collaborative filtering, which exploits user ratings to discover latent factors in the data.

Collaborative Filtering Recommendation Systems

node2coords: Graph Representation Learning with Wasserstein Barycenters

no code implementations31 Jul 2020 Effrosyni Simou, Dorina Thanou, Pascal Frossard

In the decoder, the node connectivity descriptors are reconstructed as Wasserstein barycenters of the graph structural patterns.

Decoder Graph Representation Learning +1

Graph signal processing for machine learning: A review and new perspectives

no code implementations31 Jul 2020 Xiaowen Dong, Dorina Thanou, Laura Toni, Michael Bronstein, Pascal Frossard

The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning.

BIG-bench Machine Learning Computational Efficiency

Towards robust sensing for Autonomous Vehicles: An adversarial perspective

no code implementations14 Jul 2020 Apostolos Modas, Ricardo Sanchez-Matilla, Pascal Frossard, Andrea Cavallaro

Autonomous Vehicles rely on accurate and robust sensor observations for safety critical decision-making in a variety of conditions.

Autonomous Vehicles Decision Making

Building powerful and equivariant graph neural networks with structural message-passing

1 code implementation NeurIPS 2020 Clement Vignac, Andreas Loukas, Pascal Frossard

We address this problem and propose a powerful and equivariant message-passing framework based on two ideas: first, we propagate a one-hot encoding of the nodes, in addition to the features, in order to learn a local context matrix around each node.

Graph Regression Inductive Bias

Graph Pooling with Node Proximity for Hierarchical Representation Learning

no code implementations19 Jun 2020 Xing Gao, Wenrui Dai, Chenglin Li, Hongkai Xiong, Pascal Frossard

In this paper, we propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology.

Graph Classification Representation Learning

Neural Anisotropy Directions

2 code implementations NeurIPS 2020 Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers.

Inductive Bias

GeoDA: a geometric framework for black-box adversarial attacks

1 code implementation CVPR 2020 Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Huaiyu Dai

We propose a geometric framework to generate adversarial examples in one of the most challenging black-box settings where the adversary can only generate a small number of queries, each of them returning the top-$1$ label of the classifier.

Wasserstein-based Graph Alignment

no code implementations12 Mar 2020 Hermina Petric Maretic, Mireille El Gheche, Matthias Minder, Giovanni Chierchia, Pascal Frossard

We propose a novel method for comparing non-aligned graphs of different sizes, based on the Wasserstein distance between graph signal distributions induced by the respective graph Laplacian matrices.

Graph Classification

Hold me tight! Influence of discriminative features on deep network boundaries

1 code implementation NeurIPS 2020 Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates dataset features to the distance of samples to the decision boundary.

Adversarial Robustness

Joint Graph-based Depth Refinement and Normal Estimation

no code implementations CVPR 2020 Mattia Rossi, Mireille El Gheche, Andreas Kuhn, Pascal Frossard

Depth estimation is an essential component in understanding the 3D geometry of a scene, with numerous applications in urban and indoor settings.

Depth Estimation

Multi-view shape estimation of transparent containers

1 code implementation27 Nov 2019 Alessio Xompero, Ricardo Sanchez-Matilla, Apostolos Modas, Pascal Frossard, Andrea Cavallaro

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.

Semantic Segmentation

On the choice of graph neural network architectures

2 code implementations13 Nov 2019 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.

Graph Neural Network Node Classification

Imperceptible Adversarial Attacks on Tabular Data

1 code implementation8 Nov 2019 Vincent Ballet, Xavier Renard, Jonathan Aigrain, Thibault Laugel, Pascal Frossard, Marcin Detyniecki

Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions.

BIG-bench Machine Learning

Mask Combination of Multi-layer Graphs for Global Structure Inference

1 code implementation22 Oct 2019 Eda Bayram, Dorina Thanou, Elif Vural, Pascal Frossard

Structure inference is an important task for network data processing and analysis in data science.

Forward-Backward Splitting for Optimal Transport based Problems

no code implementations20 Sep 2019 Guillermo Ortiz-Jimenez, Mireille El Gheche, Effrosyni Simou, Hermina Petric Maretic, Pascal Frossard

Experiments show that the proposed method leads to a significant improvement in terms of speed and performance with respect to the state of the art for domain adaptation on a continually rotating distribution coming from the standard two moon dataset.

Domain Adaptation

iPool -- Information-based Pooling in Hierarchical Graph Neural Networks

no code implementations1 Jul 2019 Xing Gao, Hongkai Xiong, Pascal Frossard

In this paper, we propose a parameter-free pooling operator, called iPool, that permits to retain the most informative features in arbitrary graphs.

Graph Classification

Geometry aware convolutional filters for omnidirectional images representation

no code implementations ICLR 2019 Renata Khasanova, Pascal Frossard

In particular we propose an algorithm that adapts convolutional layers, which often serve as a core building block of a CNN, to the properties of omnidirectional images.

Autonomous Vehicles Image Classification

A geometry-inspired decision-based attack

1 code implementation ICCV 2019 Yujia Liu, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

The qFool method can drastically reduce the number of queries compared to previous decision-based attacks while reaching the same quality of adversarial examples.

General Classification Image Classification

Graph heat mixture model learning

no code implementations24 Jan 2019 Hermina Petric Maretic, Mireille El Gheche, Pascal Frossard

Graph inference methods have recently attracted a great interest from the scientific community, due to the large value they bring in data interpretation and analysis.

SparseFool: a few pixels make a big difference

1 code implementation CVPR 2019 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 input data.

Image Classification

Kernel Regression for Graph Signal Prediction in Presence of Sparse Noise

no code implementations6 Nov 2018 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.


OrthoNet: Multilayer Network Data Clustering

no code implementations2 Nov 2018 Mireille El Gheche, Giovanni Chierchia, Pascal Frossard

We propose in this paper to extend the node clustering problem, that commonly considers only the network information, to a problem where both the network information and the node features are considered together for learning a clustering-friendly representation of the feature space.

Clustering Graph Clustering +1

Graph Laplacian mixture model

1 code implementation23 Oct 2018 Hermina Petric Maretic, Pascal Frossard

Graph learning methods have recently been receiving increasing interest as means to infer structure in datasets.

Clustering Graph Learning

Isometric Transformation Invariant Graph-based Deep Neural Network

no code implementations21 Aug 2018 Renata Khasanova, Pascal Frossard

In this work we present a novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images.

General Classification Translation +1

Learning graphs from data: A signal representation perspective

no code implementations3 Jun 2018 Xiaowen Dong, Dorina Thanou, Michael Rabbat, Pascal Frossard

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

Graph Learning

Empirical Study of the Topology and Geometry of Deep Networks

no code implementations CVPR 2018 Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Stefano Soatto

We specifically study the topology of classification regions created by deep networks, as well as their associated decision boundary.

General Classification

Adaptive Quantization for Deep Neural Network

no code implementations4 Dec 2017 Yiren Zhou, Seyed-Mohsen Moosavi-Dezfooli, Ngai-Man Cheung, Pascal Frossard

First, we propose a measurement to estimate the effect of parameter quantization errors in individual layers on the overall model prediction accuracy.


Graph Signal Processing: Overview, Challenges and Applications

2 code implementations1 Dec 2017 Antonio Ortega, Pascal Frossard, Jelena Kovačević, José M. F. Moura, Pierre Vandergheynst

Research in Graph Signal Processing (GSP) aims to develop tools for processing data defined on irregular graph domains.

Signal Processing

Geometric robustness of deep networks: analysis and improvement

1 code implementation CVPR 2018 Can Kanbak, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

We propose ManiFool as a simple yet scalable algorithm to measure the invariance of deep networks.

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

no code implementations27 Oct 2017 Bastien Pasdeloup, Vincent Gripon, Jean-Charles Vialatte, Dominique Pastor, Pascal Frossard

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


Graph-Based Classification of Omnidirectional Images

no code implementations26 Jul 2017 Renata Khasanova, Pascal Frossard

Omnidirectional cameras are widely used in such areas as robotics and virtual reality as they provide a wide field of view.

Classification General Classification +2

Graph learning under sparsity priors

1 code implementation18 Jul 2017 Hermina Petric Maretic, Dorina Thanou, Pascal Frossard

If this is not possible, the data structure has to be inferred from the mere signal observations.

Graph Learning

Classification regions of deep neural networks

no code implementations26 May 2017 Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, Stefano Soatto

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space.

Classification General Classification

Robustness of classifiers to universal perturbations: a geometric perspective

no code implementations ICLR 2018 Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, Stefano Soatto

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 misclassified by such classifiers.

Light Field Super-Resolution Via Graph-Based Regularization

no code implementations9 Jan 2017 Mattia Rossi, Pascal Frossard

We adopt a multi-frame alike super-resolution approach, where the complementary information in the different light field views is used to augment the spatial resolution of the whole light field.

Depth Estimation Disparity Estimation +1

Learning heat diffusion graphs

no code implementations4 Nov 2016 Dorina Thanou, Xiaowen Dong, Daniel Kressner, Pascal Frossard

Effective information analysis generally boils down to properly identifying the structure or geometry of the data, which is often represented by a graph.

Graph Learning

Universal adversarial perturbations

10 code implementations CVPR 2017 Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard

Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability.

Robustness of classifiers: from adversarial to random noise

no code implementations NeurIPS 2016 Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

Moreover, we quantify the robustness of classifiers in terms of the subspace dimension in the semi-random noise regime, and show that our bounds remarkably interpolate between the worst-case and random noise regimes.

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

no code implementations12 Jul 2016 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.

Image Retrieval Retrieval

Manitest: Are classifiers really invariant?

no code implementations23 Jul 2015 Alhussein Fawzi, Pascal Frossard

Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks.

Data Augmentation

Graph-based compression of dynamic 3D point cloud sequences

no code implementations19 Jun 2015 Dorina Thanou, Philip A. Chou, Pascal Frossard

This paper addresses the problem of compression of 3D point cloud sequences that are characterized by moving 3D positions and color attributes.

Motion Estimation

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

no code implementations19 May 2015 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 functions.

Additive models Dictionary Learning +2

Analysis of classifiers' robustness to adversarial perturbations

no code implementations9 Feb 2015 Alhussein Fawzi, Omar Fawzi, Pascal Frossard

To the best of our knowledge, our results provide the first theoretical work that addresses the phenomenon of adversarial instability recently observed for deep networks.

General Classification

Learning Laplacian Matrix in Smooth Graph Signal Representations

2 code implementations30 Jun 2014 Xiaowen Dong, Dorina Thanou, Pascal Frossard, Pierre Vandergheynst

We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals.

Graph Learning

Multiscale Event Detection in Social Media

no code implementations25 Apr 2014 Xiaowen Dong, Dimitrios Mavroeidis, Francesco Calabrese, Pascal Frossard

In this paper, we propose a novel approach towards multiscale event detection using social media data, which takes into account different temporal and spatial scales of events in the data.

Clustering Event Detection

Dictionary learning for fast classification based on soft-thresholding

no code implementations9 Feb 2014 Alhussein Fawzi, Mike Davies, Pascal Frossard

The dictionary learning problem, which jointly learns the dictionary and linear classifier, is cast as a difference of convex (DC) program and solved efficiently with an iterative DC solver.

Classification Dictionary Learning +1

A Study of Image Analysis with Tangent Distance

no code implementations11 Jan 2014 Elif Vural, Pascal Frossard

As theoretical studies about the tangent distance algorithm have been largely overlooked, we present in this work a detailed performance analysis of this useful algorithm, which can eventually help its implementation.

Image Classification Image Registration

Learning parametric dictionaries for graph signals

1 code implementation5 Jan 2014 Dorina Thanou, David I Shuman, Pascal Frossard

In sparse signal representation, the choice of a dictionary often involves a tradeoff between two desirable properties -- the ability to adapt to specific signal data and a fast implementation of the dictionary.

Denoising Dictionary Learning

Analysis of Descent-Based Image Registration

no code implementations15 Feb 2013 Elif Vural, Pascal Frossard

We show that the area of this neighborhood increases at least quadratically with the smoothing filter size, which justifies the use of a smoothing step in image registration with local optimizers such as gradient descent.

Image Registration Translation

Image registration with sparse approximations in parametric dictionaries

no code implementations28 Jan 2013 Alhussein Fawzi, Pascal Frossard

We examine in this paper the problem of image registration from the new perspective where images are given by sparse approximations in parametric dictionaries of geometric functions.

Image Registration

Tangent-based manifold approximation with locally linear models

1 code implementation6 Nov 2012 Sofia Karygianni, Pascal Frossard

Our objective is to discover a set of low dimensional affine subspaces that represents manifold data accurately while preserving the manifold's structure.

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

1 code implementation31 Oct 2012 David I Shuman, Sunil K. Narang, Pascal Frossard, Antonio Ortega, Pierre Vandergheynst

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


Navigation domain representation for interactive multiview imaging

no code implementations18 Oct 2012 Thomas Maugey, Ismael Daribo, Gene Cheung, Pascal Frossard

In this paper, we propose a novel multiview data representation that permits to satisfy bandwidth and storage constraints in an interactive multiview streaming system.

Decoder Navigate

Cannot find the paper you are looking for? You can Submit a new open access paper.