中文
相关论文

相关论文: SInGE: Sparsity via Integrated Gradients Estimatio…

200 篇论文

Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular…

神经与进化计算 · 计算机科学 2015-12-31 Sajid Anwar , Kyuyeon Hwang , Wonyong Sung

Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks. Due to the complexity of current network architectures, current gradient-based…

计算机视觉与模式识别 · 计算机科学 2020-03-10 Ashkan Khakzar , Soroosh Baselizadeh , Saurabh Khanduja , Christian Rupprecht , Seong Tae Kim , Nassir Navab

Recent advancements have scaled neural networks to unprecedented sizes, achieving remarkable performance across a wide range of tasks. However, deploying these large-scale models on resource-constrained devices poses significant challenges…

机器学习 · 计算机科学 2024-10-22 Mostafa Hussien , Mahmoud Afifi , Kim Khoa Nguyen , Mohamed Cheriet

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…

The remarkable performance of modern deep neural networks (DNNs) is largely driven by their massive scale, often comprising tens to hundreds of millions-or even billions-of parameters. However, such a scale incurs substantial storage and…

机器学习 · 计算机科学 2026-05-01 Mingyuan Wang , Yangzi Guo , Sida Liu , Yuhang Liu

Spiking Neural Networks (SNNs) have gained significant attention due to the energy-efficient and multiplication-free characteristics. Despite these advantages, deploying large-scale SNNs on edge hardware is challenging due to limited…

神经与进化计算 · 计算机科学 2024-11-22 Shuo Chen , Boxiao Liu , Zeshi Liu , Haihang You

Pruning large neural networks while maintaining their performance is often desirable due to the reduced space and time complexity. In existing methods, pruning is done within an iterative optimization procedure with either heuristically…

计算机视觉与模式识别 · 计算机科学 2019-02-26 Namhoon Lee , Thalaiyasingam Ajanthan , Philip H. S. Torr

Spiking Neural Networks (SNNs) have been attached great importance due to their biological plausibility and high energy-efficiency on neuromorphic chips. As these chips are usually resource-constrained, the compression of SNNs is thus…

神经与进化计算 · 计算机科学 2021-08-19 Yanqi Chen , Zhaofei Yu , Wei Fang , Tiejun Huang , Yonghong Tian

To reduce the significant redundancy in deep Convolutional Neural Networks (CNNs), most existing methods prune neurons by only considering statistics of an individual layer or two consecutive layers (e.g., prune one layer to minimize the…

计算机视觉与模式识别 · 计算机科学 2018-03-23 Ruichi Yu , Ang Li , Chun-Fu Chen , Jui-Hsin Lai , Vlad I. Morariu , Xintong Han , Mingfei Gao , Ching-Yung Lin , Larry S. Davis

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…

机器学习 · 计算机科学 2020-10-13 Sai Aparna Aketi , Sourjya Roy , Anand Raghunathan , Kaushik Roy

Neural networks (NNs) are making a large impact both on research and industry. Nevertheless, as NNs' accuracy increases, it is followed by an expansion in their size, required number of compute operations and energy consumption. Increase in…

机器学习 · 计算机科学 2021-12-21 Martin Ferianc , Anush Sankaran , Olivier Mastropietro , Ehsan Saboori , Quentin Cappart

We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy. Our algorithm uses a small batch of input points to construct a data-informed…

机器学习 · 计算机科学 2021-03-16 Cenk Baykal , Lucas Liebenwein , Igor Gilitschenski , Dan Feldman , Daniela Rus

Deep neural networks (DNNs) demonstrate outstanding performance across most computer vision tasks. Some critical applications, such as autonomous driving or medical imaging, also require investigation into their behavior and the reasons…

计算机视觉与模式识别 · 计算机科学 2023-12-11 Edouard Yvinec , Arnaud Dapogny , Kevin Bailly , Xavier Fischer

Deep neural networks (DNNs) have demonstrated remarkable success, yet their wide adoption is often hindered by their opaque decision-making. To address this, attribution methods have been proposed to assign relevance values to each part of…

计算机视觉与模式识别 · 计算机科学 2025-04-10 Danielle Cohen , Hila Chefer , Lior Wolf

The remarkable performance of deep Convolutional neural networks (CNNs) is generally attributed to their deeper and wider architectures, which can come with significant computational costs. Pruning neural networks has thus gained interest…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Yang He , Lingao Xiao

With the introduction of SNIP [arXiv:1810.02340v2], it has been demonstrated that modern neural networks can effectively be pruned before training. Yet, its sensitivity criterion has since been criticized for not propagating training signal…

机器学习 · 计算机科学 2020-06-16 Stijn Verdenius , Maarten Stol , Patrick Forré

The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to the vast amount of parameters that characterize model…

机器学习 · 计算机科学 2026-02-25 Enrico Ballini , Luca Muscarnera , Alessio Fumagalli , Anna Scotti , Francesco Regazzoni

Explainability is a key component in many applications involving deep neural networks (DNNs). However, current explanation methods for DNNs commonly leave it to the human observer to distinguish relevant explanations from spurious noise.…

机器学习 · 计算机科学 2025-10-22 Paulo Yanez Sarmiento , Simon Witzke , Nadja Klein , Bernhard Y. Renard

Deep convolutional neural networks have liberated its extraordinary power on various tasks. However, it is still very challenging to deploy state-of-the-art models into real-world applications due to their high computational complexity. How…

计算机视觉与模式识别 · 计算机科学 2018-09-06 Zehao Huang , Naiyan Wang

Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference. Pruning a proportion of unimportant filters is an efficient way to mitigate the inference…

计算机视觉与模式识别 · 计算机科学 2020-05-07 Kai Zhao , Xin-Yu Zhang , Qi Han , Ming-Ming Cheng
‹ 上一页 1 2 3 10 下一页 ›