Publications associées à Graph Transform Learning for Image Compression

Publications associées (19)

SPEEDING UP KRYLOV SUBSPACE METHODS FOR COMPUTING f(A)b VIA RANDOMIZATION

This work is concerned with the computation of the action of a matrix function f(A), such as the matrix exponential or the matrix square root, on a vector b. For a general matrix A, this can be done by computing the compression of A onto a suitable Krylov ...

Siam Publications2024

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis

Mathew Magimai Doss, Eklavya Sarkar

Marmoset monkeys encode vital information in their calls and serve as a surrogate model for neuro-biologists to understand the evolutionary origins of human vocal communication. Traditionally analyzed with signal processing-based features, recent approache ...

2024

The JPEG AI Standard: Providing Efficient Human and Machine Visual Data Consumption

Touradj Ebrahimi

The Joint Photographic Experts Group (JPEG) AI learning-based image coding system is an ongoing joint standardization effort between International Organization for Standardization (ISO), International Electrotechnical Commission (IEC), and International Te ...

IEEE COMPUTER SOC2023

Shafranov shift correction to the Furth-Yoshikawa scaling of tokamak adiabatic compression

Olivier Sauter

In 1970, Furth and Yoshikawa (1970 Phys. Fluids 13 2593-6) introduced the scalings of adiabatic plasma compression. Basically, if the shape of the external plasma boundary and the aspect ratio are preserved during the compression, then the density, kinetic ...

2023

Compressed Distributed Regression over Adaptive Networks

Ali H. Sayed

We examine the learning performance achievable by a network of agents that solve a distributed regression problem using the recently proposed ACTC (Adapt-Compress-Then-Combine) diffusion strategy. The agents operate under communication constraints: they ar ...

IEEE2023

A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning

Jean-Philippe Thiran, Roser Vinals Terres

Ultrafast ultrasound imaging, characterized by high frame rates, generates low-quality images. Convolutional neural networks (CNNs) have demonstrated great potential to enhance image quality without compromising the frame rate. However, CNNs have been most ...

2023

Experimental investigation of two-dimensional Mode-II delamination in composite laminates

Thomas Keller, Anastasios Vassilopoulos, Congzhe Wang

The two-dimensional (2D) delamination growth in composite laminates under the Mode-II fracture condition was experimentally investigated using a novel set-up. Circular plate specimens with a centrally embedded pre-crack of two sizes were semi-clamped along ...

2023

Landmarking for Navigational Streaming of Stored High-Dimensional Media

Pascal Frossard, Yuan Yuan

Modern media data such as 360 degrees videos and light field (LF) images are typically captured in much higher dimensions than the observers' visual displays. To efficiently browse high-dimensional media, a navigational streaming model is considered: a cli ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks

Chen Liu

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning. However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep ...

EPFL2022

Secrecy by Design With Applications to Privacy and Compression

Yanina Yurina Shkel

Secrecy by design is examined as an approach to information-theoretic secrecy. The main idea behind this approach is to design an information processing system from the ground up to be perfectly secure with respect to an explicit secrecy constraint. The pr ...

2021

Image Compression and Quality Assessment using Convolutional Neural Networks

Pinar Akyazi

The rapid development of digital imaging and video has placed visual contents in the heart of our lives. Digital multimedia span a vast number of areas from business to leisure, including but not limited to education, medicine, accessibility, training, adv ...

EPFL2020

Comprehensive assessment of image compression algorithms

Touradj Ebrahimi, Michela Testolina, Evgeniy Upenik

JPEG image coding standard has been a dominant format in a wide range of applications in soon three decades since it has been released as an international standard. The landscape of applications and services based on pictures has evolved since the original ...

SPIE2020

Comparison of Interactive Subjective Methodologies for Light Field Quality Evaluation

Touradj Ebrahimi, Irene Viola

The recent advances in light field acquisition and rendering technologies have attracted a lot of interest from the scientific community. Due to their large amount of data, efficient compression of light field content is of paramount importance for storage ...

2018

Privacy-Friendly Photo Sharing and Relevant Applications Beyond

Lin Yuan

Popularization of online photo sharing brings people great convenience, but has also raised concerns for privacy. Researchers proposed various approaches to enable image privacy, most of which focus on encrypting or distorting image visual content. In this ...

EPFL2017

Improved temporal resolution for functional studies with reduced number of segments with three-dimensional echo planar imaging

Rolf Gruetter, Tobias Kober, Wietske Van der Zwaag, José Pedro Rebelo Ferreira Marques, Mayur Narsude

PURPOSE: To introduce a new k-space traversal strategy for segmented three-dimensional echo planar imaging (3D EPI) that encodes two partitions per radiofrequency excitation, effectively reducing the number excitations used to acquire a 3D EPI dataset by h ...

Wiley-Blackwell2014

An Evaluation of Model-Based Approaches to Sensor Data Compression

Karl Aberer, Quoc Viet Hung Nguyen, Ho Young Jeung

As the volumes of sensor data being accumulated are likely to soar, data compression has become essential in a wide range of sensor-data applications. This has led to a plethora of data compression techniques for sensor data, in particular model-based appr ...

Institute of Electrical and Electronics Engineers2013

Polar Codes are Optimal for Lossy Source Coding

Rüdiger Urbanke

We consider lossy source compression of a binary symmetric source with Hamming distortion function. We show that polar codes combined with a low-complexity successive cancellation encoding algorithm achieve the rate-distortion bound. The complexity of both ...

2009

Lower Bounds on the Rate-Distortion Function of Individual LDGM Codes

Rüdiger Urbanke, Shrinivas Kudekar

We consider lossy compression of a binary symmetric source by means of a low-density generator-matrix code. We derive two lower bounds on the rate distortion function which are valid for any low-density generator-matrix code with a given node degree distri ...

2008

Directionlets : anisotropic multi-directional representation with separable filtering

Vladan Velisavljevic

Efficient representation of geometrical information in images is very important in many image processing areas, including compression, denoising and feature extraction. However, the design of transforms that can capture these geometrical features and repre ...

EPFL2005