English
Related papers

Related papers: Neuron Merging: Compensating for Pruned Neurons

200 papers

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian…

Machine Learning · Computer Science 2022-06-28 Alexander Munteanu , Simon Omlor , Zhao Song , David P. Woodruff

Residual Networks with convolutional layers are widely used in the field of machine learning. Since they effectively extract features from input data by stacking multiple layers, they can achieve high accuracy in many applications. However,…

Machine Learning · Computer Science 2019-06-11 Yasutoshi Ida , Yasuhiro Fujiwara

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression…

Computer Vision and Pattern Recognition · Computer Science 2022-11-16 Yihui He

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Junzhu Mao , Yang Shen , Jinyang Guo , Yazhou Yao , Xiansheng Hua

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Seul-Ki Yeom , Kyung-Hwan Shim , Jee-Hyun Hwang

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations. The key idea is to rank the filters based on a certain criterion (say, $l_1$-norm, average…

Computer Vision and Pattern Recognition · Computer Science 2018-02-01 Deepak Mittal , Shweta Bhardwaj , Mitesh M. Khapra , Balaraman Ravindran

We propose a modularization method that decomposes a deep neural network (DNN) into small modules from a functionality perspective and recomposes them into a new model for some other task. Decomposed modules are expected to have the…

Machine Learning · Computer Science 2021-12-28 Hiroaki Kingetsu , Kenichi Kobayashi , Taiji Suzuki

This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…

Computer Vision and Pattern Recognition · Computer Science 2018-02-22 Babajide O. Ayinde , Jacek M. Zurada

The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Nathan Hubens , Victor Delvigne , Matei Mancas , Bernard Gosselin , Marius Preda , Titus Zaharia

For convolutional neural networks (CNNs) that have a large volume of input data, memory management becomes a major concern. Memory cost reduction can be an effective way to deal with these problems that can be realized through different…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 Emad MalekHosseini , Mohsen Hajabdollahi , Nader Karimi , Shadrokh Samavi , Shahram Shirani

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Zechun Liu , Haoyuan Mu , Xiangyu Zhang , Zichao Guo , Xin Yang , Tim Kwang-Ting Cheng , Jian Sun

Incorporation of a new knowledge into neural networks with simultaneous preservation of the previous one is known to be a nontrivial problem. This problem becomes even more complex when new knowledge is contained not in new training…

Machine Learning · Computer Science 2019-09-10 Mikhail Iu. Leontev , Viktoriia Islenteva , Sergey V. Sukhov

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources. To enable the deployment of modern models on resource-constrained…

Machine Learning · Computer Science 2024-08-12 Hongrong Cheng , Miao Zhang , Javen Qinfeng Shi

Channel pruning is widely used to reduce the complexity of deep network models. Recent pruning methods usually identify which parts of the network to discard by proposing a channel importance criterion. However, recent studies have shown…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Yuanzhi Duan , Yue Zhou , Peng He , Qiang Liu , Shukai Duan , Xiaofang Hu

Rectified Linear Units (ReLU) are the default choice for activation functions in deep neural networks. While they demonstrate excellent empirical performance, ReLU activations can fall victim to the dead neuron problem. In these cases, the…

Machine Learning · Computer Science 2023-02-14 Tim Whitaker , Darrell Whitley

One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements. Deep CNNs can either be pruned width-wise by removing filters based on…

Computer Vision and Pattern Recognition · Computer Science 2020-10-07 Muhammad Umair Haider , Murtaza Taj

To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and…

Machine Learning · Computer Science 2019-08-08 Yunxiang Zhang , Chenglong Zhao , Bingbing Ni , Jian Zhang , Haoran Deng

Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and memory resources,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Hichem Sahbi

This paper presents a method for adding multiple tasks to a single deep neural network while avoiding catastrophic forgetting. Inspired by network pruning techniques, we exploit redundancies in large deep networks to free up parameters that…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Arun Mallya , Svetlana Lazebnik
‹ Prev 1 8 9 10 Next ›