English
Related papers

Related papers: FastNet

200 papers

Deep models have achieved significant process on single image super-resolution (SISR) tasks, in particular large models with large kernel ($3\times3$ or more). However, the heavy computational footprint of such models prevents their…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Gang Wu , Junjun Jiang , Kui Jiang , Xianming Liu

Classification performance based on ImageNet is the de-facto standard metric for CNN development. In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Lukas Tuggener , Jürgen Schmidhuber , Thilo Stadelmann

We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including…

Machine Learning · Computer Science 2017-03-01 Corinna Cortes , Xavi Gonzalvo , Vitaly Kuznetsov , Mehryar Mohri , Scott Yang

The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS methods relax the categorical choice of a particular…

Computer Vision and Pattern Recognition · Computer Science 2019-12-11 Shoufa Chen , Yunpeng Chen , Shuicheng Yan , Jiashi Feng

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various…

Computer Vision and Pattern Recognition · Computer Science 2015-12-14 Christian Szegedy , Vincent Vanhoucke , Sergey Ioffe , Jonathon Shlens , Zbigniew Wojna

One of the main challenges since the advancement of convolutional neural networks is how to connect the extracted feature map to the final classification layer. VGG models used two sets of fully connected layers for the classification part…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Mohammad Rahimzadeh , AmirAli Askari , Soroush Parvin , Elnaz Safi , Mohammad Reza Mohammadi

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Machine Learning · Computer Science 2026-03-17 Jérémy Morlier , Robin Geens , Stef Cuyckens , Arne Symons , Marian Verhelst , Vincent Gripon , Mathieu Léonardon

Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Pouya Shiri , Amirali Baniasadi

The performance of convolutional neural networks (CNN) depends heavily on their architectures. Transfer learning performance of a CNN relies quite strongly on selection of its trainable layers. Selecting the most effective update layers for…

Machine Learning · Computer Science 2023-03-02 Md. Mehedi Hasana , Muhammad Ibrahim , Md. Sawkat Ali

In the recent past, the success of Neural Architecture Search (NAS) has enabled researchers to broadly explore the design space using learning-based methods. Apart from finding better neural network architectures, the idea of automation has…

Machine Learning · Computer Science 2019-11-04 Qing Lu , Weiwen Jiang , Xiaowei Xu , Yiyu Shi , Jingtong Hu

Deep neural networks (DNNs) have become ubiquitous thanks to their remarkable ability to model complex patterns across various domains such as computer vision, speech recognition, robotics, etc. While large DNN models are often more…

Machine Learning · Computer Science 2025-11-18 Omkar Shende , Gayathri Ananthanarayanan , Marcello Traiola

Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…

Computer Vision and Pattern Recognition · Computer Science 2017-06-13 David Budden , Alexander Matveev , Shibani Santurkar , Shraman Ray Chaudhuri , Nir Shavit

Designing architectures for deep neural networks requires expert knowledge and substantial computation time. We propose a technique to accelerate architecture selection by learning an auxiliary HyperNet that generates the weights of a main…

Machine Learning · Computer Science 2017-08-18 Andrew Brock , Theodore Lim , J. M. Ritchie , Nick Weston

In-memory computing is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. Crossbar arrays of resistive memory devices can be used to encode the network weights and perform efficient analog…

Convolutional Neural Networks, or CNNs, are the state of the art for image classification, but typically come at the cost of a large memory footprint. This limits their usefulness in applications relying on embedded devices, where memory is…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Sebastian Müksch , Theo Olausson , John Wilhelm , Pavlos Andreadis

Convolutional Neural Networks (CNNs) have produced state-of-the-art results for image classification tasks. However, they are limited in their ability to handle rotational and viewpoint variations due to information loss in max-pooling…

Machine Learning · Computer Science 2023-10-06 Samaneh Javadinia , Amirali Baniasadi

Deep Neural Networks (DNNs) have been widely deployed for many Machine Learning applications. Recently, CapsuleNets have overtaken traditional DNNs, because of their improved generalization ability due to the multi-dimensional capsules, in…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-01-26 Alberto Marchisio , Muhammad Abdullah Hanif , Muhammad Shafique

Fully Connected Neural Networks (FCNNs) have been the core of most state-of-the-art Machine Learning (ML) applications in recent years and also have been widely used for Intrusion Detection Systems (IDSs). Experimental results from the last…

Machine Learning · Computer Science 2020-10-16 Fares Meghdouri , Maximilian Bachl , Tanja Zseby

Residual neural networks are widely used in computer vision tasks. They enable the construction of deeper and more accurate models by mitigating the vanishing gradient problem. Their main innovation is the residual block which allows the…

Hardware Architecture · Computer Science 2023-11-03 Filippo Minnella , Teodoro Urso , Mihai T. Lazarescu , Luciano Lavagno

Neural architecture search (NAS) has become a common approach to developing and discovering new neural architectures for different target platforms and purposes. However, scanning the search space is comprised of long training processes of…

Computer Vision and Pattern Recognition · Computer Science 2022-09-29 Tal Hakim