no code implementations • 18 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.
1 code implementation • 31 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.
1 code implementation • 6 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.
no code implementations • 28 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.
no code implementations • 15 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.
1 code implementation • 5 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.
no code implementations • 11 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.
no code implementations • 9 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.
no code implementations • 25 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.
2 code implementations • 30 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.
no code implementations • 9 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.
no code implementations • 19 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.
no code implementations • 19 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.
no code implementations • 23 Jul 2015 • Alhussein Fawzi, Pascal Frossard
Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks.
3 code implementations • CVPR 2016 • Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal Frossard
State-of-the-art deep neural networks have achieved impressive results on many image classification tasks.
no code implementations • 12 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.
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.
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.
no code implementations • 4 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.
no code implementations • 9 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.
no code implementations • ICML 2017 • Renata Khasanova, Pascal Frossard
Learning transformation invariant representations of visual data is an important problem in computer vision.
no code implementations • 26 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.
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.
1 code implementation • 18 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.
no code implementations • 26 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.
no code implementations • 27 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.
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.
2 code implementations • 1 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
no code implementations • 4 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.
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.
no code implementations • 3 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.
no code implementations • 21 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.
1 code implementation • 23 Oct 2018 • Hermina Petric Maretic, Pascal Frossard
Graph learning methods have recently been receiving increasing interest as means to infer structure in datasets.
no code implementations • 2 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.
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.
no code implementations • 6 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.
1 code implementation • CVPR 2019 • Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Jonathan Uesato, Pascal Frossard
State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations.
no code implementations • 13 Dec 2018 • Mireille El Gheche, Giovanni Chierchia, Pascal Frossard
In this paper, we propose a scalable algorithm for spectral embedding.
no code implementations • 24 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.
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.
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.
1 code implementation • NeurIPS 2019 • Hermina Petric Maretic, Mireille El Gheche, Giovanni Chierchia, Pascal Frossard
We present a novel framework based on optimal transport for the challenging problem of comparing graphs.
no code implementations • 1 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.
no code implementations • 20 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.
1 code implementation • 22 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.
1 code implementation • 8 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.
2 code implementations • 13 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.
1 code implementation • 27 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.
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.
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.
no code implementations • 12 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.
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.
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.
no code implementations • 19 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.
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.
no code implementations • 14 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.
no code implementations • 31 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.
no code implementations • 31 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.
1 code implementation • 13 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.
no code implementations • 14 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.
no code implementations • 19 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.
no code implementations • 29 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.
no code implementations • 29 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.
no code implementations • 24 Dec 2020 • Yves Rychener, Xavier Renard, Djamé Seddah, Pascal Frossard, Marcin Detyniecki
NLP Interpretability aims to increase trust in model predictions.
1 code implementation • 24 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.
no code implementations • 8 Feb 2021 • Apostolos Modas, Alessio Xompero, Ricardo Sanchez-Matilla, Pascal Frossard, Andrea Cavallaro
We investigate the problem of classifying - from a single image - the level of content in a cup or a drinking glass.
no code implementations • 9 Mar 2021 • Beril Besbinar, Pascal Frossard
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data.
no code implementations • 16 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.
no code implementations • 27 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.
no code implementations • 30 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.
2 code implementations • 27 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)
no code implementations • 29 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?
no code implementations • 28 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.
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.
no code implementations • 18 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.
no code implementations • 28 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.
no code implementations • 19 Jul 2021 • Navid Mahmoudian Bidgoli, Roberto G. de A. Azevedo, Thomas Maugey, Aline Roumy, Pascal Frossard
State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs).
no code implementations • 3 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.
2 code implementations • 9 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.
no code implementations • 29 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.
no code implementations • 29 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.
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.
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.
no code implementations • 11 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.
1 code implementation • 27 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.
Ranked #28 on Domain Generalization on ImageNet-C
no code implementations • 8 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.
1 code implementation • 11 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.
no code implementations • 14 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.
1 code implementation • 22 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.
1 code implementation • 23 Mar 2022 • Ahmet Caner Yüzügüler, Nikolaos Dimitriadis, Pascal Frossard
Optimizing resource utilization in target platforms is key to achieving high performance during DNN inference.
Hardware Aware Neural Architecture Search Image Classification +1
1 code implementation • 18 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.
no code implementations • 31 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).
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.
1 code implementation • 16 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.
1 code implementation • 29 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.
1 code implementation • 6 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.
1 code implementation • 11 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.
1 code implementation • 18 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.
no code implementations • 1 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.
no code implementations • 1 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.
1 code implementation • 6 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).
no code implementations • 18 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.
no code implementations • 7 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.
1 code implementation • 2 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.
1 code implementation • 17 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.
1 code implementation • 2 Mar 2023 • Sahar Sadrizadeh, AmirHossein Dabiri Aghdam, Ljiljana Dolamic, Pascal Frossard
In this paper, we propose a new targeted adversarial attack against NMT models.
no code implementations • 4 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.
no code implementations • 3 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.
1 code implementation • 21 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.
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.
no code implementations • 31 May 2023 • Isabel Haasler, Pascal Frossard
Finding the mean of sampled data is a fundamental task in machine learning and statistics.
1 code implementation • 12 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.
no code implementations • 13 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.
no code implementations • 14 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.
1 code implementation • 5 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.
no code implementations • 7 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.
no code implementations • 29 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.
no code implementations • 10 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.
no code implementations • 10 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.
no code implementations • 2 Nov 2023 • Abdellah Rahmani, Pascal Frossard
The task of uncovering causal relationships among multivariate time series data stands as an essential and challenging objective that cuts across a broad array of disciplines ranging from climate science to healthcare.
1 code implementation • 3 Nov 2023 • Yiming Qin, Clement Vignac, Pascal Frossard
In this work, we introduce SparseDiff, a denoising diffusion model for graph generation that is able to exploit sparsity during its training phase.
no code implementations • 3 Feb 2024 • Hugues van Assel, Cédric Vincent-Cuaz, Nicolas Courty, Rémi Flamary, Pascal Frossard, Titouan Vayer
Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets.
1 code implementation • 22 Mar 2024 • Junbo Yin, Jianbing Shen, Runnan Chen, Wei Li, Ruigang Yang, Pascal Frossard, Wenguan Wang
HSF applies Point-to-Grid and Grid-to-Region transformers to capture the multimodal scene context at different granularities.