Netscope: Practical Network Loss Tomography

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to generate instance-level explainable maps in a semantic segmentation scenario, suc ...

Tomographic imaging of time-evolving samples is a challenging yet important task for various research fields. At the nanoscale, current approaches face limitations of measurement speed or resolution due to lengthy acquisitions. We developed a dynamic nanot ...

Visual information is deeply rooted in our daily lives. From social media to medical imaging, the demand for efficient storage and transmission of visual data is increasing exponentially. Image compression is a fundamental tool for managing this enormous d ...

In this thesis, we explore techniques for addressing the communication bottleneck in data-parallel distributed training of deep learning models. We investigate algorithms that either reduce the size of the messages that are exchanged between workers, or th ...

In 1948, Claude Shannon laid the foundations of information theory, which grew out of a study to find the ultimate limits of source compression, and of reliable communication. Since then, information theory has proved itself not only as a quest to find the ...

The use of point clouds as an imaging modality has been rapidly growing, motivating research on compression methods to enable efficient transmission and storage for many applications. While compression standards relying on conven- tional techniques such as ...

The use of meteorological radars to study snowfall microphysical properties and processes is well established, in particular via a few distinct techniques: the use of radar polarimetry, of multi-frequency radar measurements, and of the radar Doppler spectr ...

Positron emission tomography is a nuclear imaging technique well known for its use in oncology for cancer diagnosis and staging. A PET scanner is a complex machine which comprises photodetectors placed in a ring configuration that detect gamma photons gen ...

The use of point clouds to digitally represent three-dimensional objects with both geometry and color attributes is rapidly increasing in several applications. Since storage and transmission of uncompressed point cloud data are often impractical, several l ...

We consider distributed optimization over several devices, each sending incremental model updates to a central server. This setting is considered, for instance, in federated learning. Various schemes have been designed to compress the model updates in orde ...

The convergence speed of machine learning models trained with Federated Learning is significantly affected by non-independent and identically distributed (non-IID) data partitions, even more so in a fully decentralized setting without a central server. In ...

Model compression techniques have lead to a reduction of size and number of computations of Deep Learning models. However, techniques such as pruning mostly lack of a real co-optimization with hardware platforms. For instance, implementing unstructured pru ...

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extra-gradient), limiting SGD updates to a sub ...

Background and objective The automated detection of atrial activations (AAs) recorded from intracardiac electrograms (IEGMs) during atrial fibrillation (AF) is challenging considering their various amplitudes, morphologies and cycle length. Activation time ...

Massive molecular testing for COVID-19 has been pointed out as fundamental to moderate the spread of the pandemic. Pooling methods can enhance testing efficiency, but they are viable only at low incidences of the disease. We propose Smart Pooling, a machin ...

The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research com ...

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not straightforward. First, omn ...

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 ...

Learning and compression are driven by the common aim of identifying and exploiting statistical regularities in data, which opens the door for fertile collaboration between these areas. A promising group of compression techniques for learning scenarios is ...

Learning-based image codecs produce different compression artifacts, when compared to the blocking and blurring degradation introduced by conventional image codecs, such as JPEG, JPEG~2000 and HEIC. In this paper, a crowdsourcing based subjective quality e ...

Netscope: Practical Network Loss Tomography

Chat with Graph Search

Exploiting XAI Maps to Improve MS Lesion Segmentation and Detection in MRI

Dynamic sparse x-ray nanotomography reveals ionomer hydration mechanism in polymer electrolyte fuel-cell catalyst

Enhancing image quality in next-generation image compression

Communication-efficient distributed training of machine learning models

Time vs. Truth: Age-Distortion Tradeoffs and Strategies for Distributed Inference

Evaluating the effect of sparse convolutions on point cloud compression

Dual-frequency spectral radar retrieval of snowfall microphysics: a physics-driven deep-learning approach

Integrated electronics for time-of-flight positron emission tomography photodetectors

Influence of Spatial Rendering on the Performance of Point Cloud Objective Quality Metrics

Stochastic distributed learning with gradient quantization and double-variance reduction

D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning

Structured and tiled-based pruning of Deep Learning models targeting FPGA implementations

Masked Training of Neural Networks with Partial Gradients

Evaluation and optimization of novel extraction algorithms for the automatic detection of atrial activations recorded within the pulmonary veins during atrial fibrillation

Smart pooling: AI-powered COVID-19 informative group testing

Latent Space Slicing for Enhanced Entropy Modeling in Learning-Based Point Cloud Geometry Compression

OSLO: On-the-Sphere Learning for Omnidirectional Images and Its Application to 360-Degree Image Compression

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks

Learning, compression, and leakage: Minimising classification error via meta-universal compression principles

Large-Scale Crowdsourcing Subjective Quality Evaluation of Learning-Based Image Coding