Pascal Frossard

Pascal Frossard

Auto-generated profile, based on publicly available information

Pascal Frossard

EPFL, Lausanne, Switzerland

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 April 2018 in Proceedings of the IEEE
Verified
Journal Article
Closed access
AOAntonio Ortega
Antonio Ortega
PFPascal Frossard
Pascal Frossard
JKJelena Kovačević
Jelena Kovačević
JMJosé M. F. Moura
José M. F. Moura
PVPierre Vandergheynst
Pierre Vandergheynst
Research in graph signal processing (GSP) aims to develop tools for processing data defined on irregular graph domains. In this paper, we first provide an overview of core ideas in GSP and their connection to conventional digital signal processing, along with a brief historical perspective to highlight how concepts recently developed in GSP build on top of prior research in other areas. We then summarize recent advances in developing basic GSP tools, including methods for sampling, filtering, or graph learning. Next, we review progress in several application areas using GSP, including processing and analysis of sensor network data, biological data, and applications to image processing and machine learning.

26 April 2019 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
XDXiaowen Dong
Xiaowen Dong
DTDorina Thanou
Dorina Thanou
MRMichael Rabbat
Michael Rabbat
PFPascal Frossard
Pascal Frossard
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 choice of the graph is not readily available from the data sets, it is thus desirable to infer or learn a graph topology from the data. In this article, we survey solutions to the problem of graph learning, including classical viewpoints from statistics and physics, and more recent approaches that adopt a graph signal processing (GSP) perspective. We further emphasize the conceptual similarities and differences between classical and GSP-based graph-inference methods and highlight the potential advantage of the latter in a number of theoretical and practical scenarios. We conclude with several open issues and challenges that are keys to the design of future signal processing and machine-learning algorithms for learning graphs from data.

29 October 2020 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
XDXiaowen Dong
Xiaowen Dong
DTDorina Thanou
Dorina Thanou
LTLaura Toni
Laura Toni
MBMichael Bronstein
Michael Bronstein
PFPascal Frossard
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. Graph signal processing (GSP), a vibrant branch of signal processing models and algorithms that aims at handling data supported on graphs, opens new paths of research to address this challenge. In this article, we review a few important contributions made by GSP concepts and tools, such as graph filters and transforms, to the development of novel machine learning algorithms. In particular, our discussion focuses on the following three aspects: exploiting data structure and relational priors, improving data and computational efficiency, and enhancing model interpretability. Furthermore, we provide new perspectives on the future development of GSP techniques that may serve as a bridge between applied mathematics and signal processing on one side and machine learning and network science on the other. Cross-fertilization across these different disciplines may help unlock the numerous challenges of complex data analysis in the modern age.

9 November 2017 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
AFAlhussein Fawzi
Alhussein Fawzi
SMSeyed-Mohsen Moosavi-Dezfooli
Seyed-Mohsen Moosavi-Dezfooli
PFPascal Frossard
Pascal Frossard
Deep neural networks have recently shown impressive classification performance on a diverse set of visual tasks. When deployed in real-world (noise-prone) environments, it is equally important that these classifiers satisfy robustness guarantees: small perturbations applied to the samples should not yield significant loss to the performance of the predictor. The goal of this article is to discuss the robustness of deep networks to a diverse set of perturbations that may affect the samples in practice, including adversarial perturbations, random noise, and geometric transformations. This article further discusses the recent works that build on the robustness analysis to provide geometric insights on the classifier's decision surface, which help in developing a better understanding of deep networks. Finally, we present recent solutions that attempt to increase the robustness of deep networks. We hope this review article will contribute to shedding light on the open research challenges in the robustness of deep networks and stir interest in the analysis of their fundamental properties.

20 April 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MRMattia Rossi
Mattia Rossi
PFPascal Frossard
Pascal Frossard
Light field cameras capture the 3D information in a scene with a single exposure. This special feature makes light field cameras very appealing for a variety of applications: from post-capture refocus, to depth estimation and image-based rendering. However, light field cameras suffer by design from strong limitations in their spatial resolution. Off-the-shelf superresolution algorithms are not ideal for light field data, as they do not consider its structure. On the other hand, the few super-resolution algorithms explicitly tailored for light field data exhibit significant limitations, such as the need to carry out a costly disparity estimation procedure with sub-pixel precision. We propose a new light field super-resolution algorithm meant to address these limitations. We use the complementary information in the different light field views to augment the spatial resolution of the whole light field at once. In particular, we show that coupling the multi-view approach with a graph-based regularizer, that enforces the light field geometric structure, permits to avoid the need of a precise and costly disparity estimation step. Extensive experiments show that the new algorithm compares favorably to the state-of-the-art methods for light field superresolution, both in terms of PSNR and visual quality.

28 September 2017 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
CLChenglin Li
Chenglin Li
LTLaura Toni
Laura Toni
JZJunni Zou
Junni Zou
HXHongkai Xiong
Hongkai Xiong
PFPascal Frossard
Pascal Frossard
Caching at mobile edge servers can smooth temporal traffic variability and reduce the service load of base stations in mobile video delivery. However, the assignment of multiple video representations to distributed servers is still a challenging question in the context of adaptive streaming, since any two representations from different videos or even from the same video will compete for the limited caching storage. Therefore it is important, yet challenging, to optimally select the cached representations for each edge server in order to effectively reduce the service load of base station while maintaining a high quality of experience (QoE) for users. To address this, we study a QoE-driven mobile edge caching placement optimization problem for dynamic adaptive video streaming that properly takes into account the different rate-distortion (R-D) characteristics of videos and the coordination among distributed edge servers. Then, by the optimal caching placement of representations for multiple videos, we maximize the aggregate average video distortion reduction of all users while minimizing the additional cost of representation downloading from the base station, subject not only to the storage capacity constraints of the edge servers, but also to the transmission and initial startup delay constraints of the users. We formulate the proposed optimization problem as an integer linear program (ILP) to provide the performance upper bound, and as a submodular maximization problem with a set of knapsack constraints to develop a practically feasible cost benefit greedy algorithm. The proposed algorithm has polynomial computational complexity and a theoretical lower bound on its performance. Simulation results further show that the proposed algorithm is able to achieve a near-optimal performance with very low time complexity. Therefore, the proposed optimization framework reveals the caching performance upper bound for general adaptive video streaming systems, while the proposed algorithm provides some design guidelines for the edge servers to select the cached representations in practice based on both the video popularity and content information.