An Accuracy-Driven Compression Methodology to Derive Efficient Codebook-Based CNNs

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.

In crowding, perception of a target deteriorates in the presence of nearby elements. As the entire stimulus configuration across large parts of the visual field influences crowding and not just nearby elements, low-level explanations, such as local pooling ...

The recent rise in interest in point clouds as an imaging modality has motivated standardization groups such as JPEG and MPEG to launch activities aiming at developing compression standards for point clouds. Lossy compression usually introduces visual arti ...

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

Electrical stimulation of the visual nervous system could improve the quality of life of patients affected by acquired blindness by restoring some visual sensations, but requires careful optimization of stimulation parameters to produce useful perceptions. ...

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 ...

Embedded memories occupy an increasingly dominant part of the area and power budgets of modern systems-on-chips (SoCs). Multi-ported embedded memories, commonly used by media SoCs and graphical processing units, occupy even more area and consume higher pow ...

Machine learning algorithms such as Convolutional Neural Networks (CNNs) are characterized by high robustness towards quantization, supporting small-bitwidth fixed-point arithmetic at inference time with little to no degradation in accuracy. In turn, small ...

The auxiliary power supply for medium voltage converters requires high insulation capability between the source and the load. Inductive power transfer technology, with an air gap between the primary and secondary coil, offers such high insulation capabilit ...

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 ...

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 the field of image acquisition, Dynamic Vision Sensors (DVS) present an innovative methodology, capturing only the variations in pixel brightness instead of absolute values and thereby revealing unique features. Given that the primary deployment of DVS ...

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

Recent advances in image compression have made it both possible and desirable for image quality to approach the visually lossless range. However, the most commonly used subjective visual quality assessment protocols, e.g. those reported in ITU-T Rec. BT.50 ...

We propose an image-based elastography method to measure the heterogeneous stiffness inside a cell and its nucleus. It uses a widely accessible setup consisting of plate compression imaged with fluorescence microscopy. Our framework recovers a spatial map ...

Visual data play a crucial role in modern society, and the rate at which images and videos are acquired, stored, and exchanged every day is rapidly increasing. Image compression is the key technology that enables storing and sharing of visual content in an ...

The past decades have witnessed rapid growth in imaging as a major form of communication between individuals. Due to recent advances in capture, storage, delivery and display technologies, consumers demand improved perceptual quality while requiring reduce ...

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 ...

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 ...

Virtual Memory (VM) is a critical programming abstraction that is widely used in various modern computing platforms. With the rise of datacenter computing and birth of planet-scale online services, the semantic and capacity requirements from memory have ev ...

An Accuracy-Driven Compression Methodology to Derive Efficient Codebook-Based CNNs

Chat with Graph Search

Does surface completion fail to support uncrowding?

Subjective performance evaluation of bitrate allocation strategies for MPEG and JPEG Pleno point cloud compression

EdgeAI-Aware Design of In-Memory Computing Architectures

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

Decoding electroencephalographic responses to visual stimuli compatible with electrical stimulation

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

Multi-Ported GC-eDRAM Bitcell with Dynamic Port Configuration and Refresh Mechanism

DBFS: Dynamic Bitwidth-Frequency Scaling for Efficient Software-defined SIMD

Modeling and optimization of PCB coils for inductive power transfer systems

Evaluating the effect of sparse convolutions on point cloud compression

Communication-efficient distributed training of machine learning models

Evaluation of the impact of lossy compression on event camera-based computer vision tasks

Modeling Structured Data in Attention-based Models

On the assessment of high-quality images: advances on the JPEG AIC-3 activity

PROBING INTRACELLULAR ELASTICITY WITH MINIMAL-HESSIAN REGISTRATION

JPEG AIC-3 Dataset: Towards Defining the High Quality to Nearly Visually Lossless Quality Range

On the Performance of Subjective Visual Quality Assessment Protocols for Nearly Visually Lossless Image Compression

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

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

Rebooting Virtual Memory with Midgard