Results 11 to 20 of about 6,914,944 (265)
Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning [PDF]
arXiv.org, 2023 The state of neural network pruning has been noticed to be unclear and even confusing for a while, largely due to"a lack of standardized benchmarks and metrics"[3].
Huan Wang, Can Qin, Yue Bai, Yun Fu
semanticscholar +1 more source
NTK-SAP: Improving neural network pruning by aligning training dynamics [PDF]
International Conference on Learning Representations, 2023 Pruning neural networks before training has received increasing interest due to its potential to reduce training time and memory. One popular method is to prune the connections based on a certain metric, but it is not entirely clear what metric is the ...
Yite Wang, Dawei Li, Ruoyu Sun
semanticscholar +1 more source
Absorption Pruning of Deep Neural Network for Object Detection in Remote Sensing Imagery
Remote Sensing, 2022 In recent years, deep convolutional neural networks (DCNNs) have been widely used for object detection tasks in remote sensing images. However, the over-parametrization problem of DCNNs hinders their application in resource-constrained remote sensing ...
Jielei Wang +4 more
doaj +1 more source
Manifold Regularized Dynamic Network Pruning [PDF]
Computer Vision and Pattern Recognition, 2021 Neural network pruning is an essential approach for reducing the computational complexity of deep models so that they can be well deployed on resource-limited devices.
Yehui Tang +6 more
semanticscholar +1 more source
Frontiers in Computational Neuroscience, 2021 Neural network pruning is critical to alleviating the high computational cost of deep neural networks on resource-limited devices. Conventional network pruning methods compress the network based on the hand-crafted rules with a pre-defined pruning ratio (
Lin Chen +3 more
doaj +1 more source
Importance Estimation for Neural Network Pruning [PDF]
Computer Vision and Pattern Recognition, 2019 Structural pruning of neural network parameters reduces computational, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with
Pavlo Molchanov +4 more
semanticscholar +1 more source
A Pruning Method for Deep Convolutional Network Based on Heat Map Generation Metrics
Sensors, 2022 With the development of deep learning, researchers design deep network structures in order to extract rich high-level semantic information. Nowadays, most popular algorithms are designed based on the complexity of visible image features.
Wenli Zhang +4 more
doaj +1 more source
Image Super-Resolution Reconstruction Algorithm Based on Sparse Neural Network [PDF]
Jisuanji gongcheng, 2022 Many deep learning-based image super-resolution reconstruction algorithms improve the overall feature expression ability of a network by extending the depth of the network.However, excessively extending the depth of the network causes the model to be ...
LI Haomin, LI Guangping
doaj +1 more source
Recent Advances on Neural Network Pruning at Initialization [PDF]
International Joint Conference on Artificial Intelligence, 2021 Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network.
Huan Wang +4 more
semanticscholar +1 more source
Roulette: A Pruning Framework to Train a Sparse Neural Network From Scratch
IEEE Access, 2021 Due to space and inference time restrictions, finding an efficient and sparse sub-network from a dense and over-parameterized network is critical for deploying neural networks on edge devices.
Qiaoling Zhong +3 more
doaj +1 more source