English

Lazy Evaluation of Convolutional Filters

Computer Vision and Pattern Recognition 2016-05-30 v1 Neural and Evolutionary Computing
Authors: Sam Leroux , Steven Bohez , Cedric De Boom , Elias De Coninck , Tim Verbelen , Bert Vankeirsbilck , Pieter Simoens , Bart Dhoedt
View on arXiv ↗ PDF ↗

Abstract

In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network. This allows to trade-off the accuracy of a deep neural network with the computational and memory requirements. This is especially important on a constrained device unable to hold all the weights of the network in memory.

Keywords

deep learning

Cite

@article{arxiv.1605.08543,
  title  = {Lazy Evaluation of Convolutional Filters},
  author = {Sam Leroux and Steven Bohez and Cedric De Boom and Elias De Coninck and Tim Verbelen and Bert Vankeirsbilck and Pieter Simoens and Bart Dhoedt},
  journal= {arXiv preprint arXiv:1605.08543},
  year   = {2016}
}

Related papers

View all related →
Computer Vision and Pattern Recognition · Computer Science
The Power of Sparsity in Convolutional Neural Networks
Soravit Changpinyo, Mark Sandler, Andrey Zhmoginov
2017-02-22
Computer Vision and Pattern Recognition · Computer Science
Learning Versatile Convolution Filters for Efficient Visual Recognition
Kai Han, Yunhe Wang, Chang Xu, Chunjing Xu +2
2021-09-23
Computer Vision and Pattern Recognition · Computer Science
Convolutional Neural Networks with Layer Reuse
Okan Köpüklü, Maryam Babaee, Stefan Hörmann, Gerhard Rigoll
2019-02-04
Emerging Technologies · Computer Science
Coupled nonlinear delay systems as deep convolutional neural networks
Bogdan Penkovsky, Xavier Porte, Maxime Jacquot, Laurent Larger +1
2019-08-07
Computer Vision and Pattern Recognition · Computer Science
Pruning Deep Neural Networks using Partial Least Squares
Artur Jordao, Ricardo Kloss, Fernando Yamada, William Robson Schwartz
2019-09-20
Computer Vision and Pattern Recognition · Computer Science
RePr: Improved Training of Convolutional Filters
Aaditya Prakash, James Storer, Dinei Florencio, Cha Zhang
2019-02-26
Machine Learning · Computer Science
Parametrizing filters of a CNN with a GAN
Yannic Kilcher, Gary Becigneul, Thomas Hofmann
2017-11-01
Computer Vision and Pattern Recognition · Computer Science
Convolutional Neural Network Pruning Using Filter Attenuation
Morteza Mousa-Pasandi, Mohsen Hajabdollahi, Nader Karimi, Shadrokh Samavi +1
2020-02-11
Computer Vision and Pattern Recognition · Computer Science
Learning to Prune Filters in Convolutional Neural Networks
Qiangui Huang, Kevin Zhou, Suya You, Ulrich Neumann
2018-01-24
Computer Vision and Pattern Recognition · Computer Science
Dependency Aware Filter Pruning
Kai Zhao, Xin-Yu Zhang, Qi Han, Ming-Ming Cheng
2020-05-07
Machine Learning · Computer Science
Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis
Mats L. Richter, Julius Schöning, Anna Wiedenroth, Ulf Krumnack
2022-06-23
Machine Learning · Computer Science
Batched Lazy Decision Trees
Mathieu Guillame-Bert, Artur Dubrawski
2016-03-09
Computer Vision and Pattern Recognition · Computer Science
An automated approach for improving the inference latency and energy efficiency of pretrained CNNs by removing irrelevant pixels with focused convolutions
Caleb Tung, Nicholas Eliopoulos, Purvish Jajal, Gowri Ramshankar +6
2023-10-13
Machine Learning · Computer Science
Complex-valued neural networks for machine learning on non-stationary physical data
Jesper Sören Dramsch, Mikael Lüthje, Anders Nymark Christensen
2020-11-17
Computer Vision and Pattern Recognition · Computer Science
Hybrid Cosine Based Convolutional Neural Networks
Adrià Ciurana, Albert Mosella-Montoro, Javier Ruiz-Hidalgo
2019-04-04
Computer Vision and Pattern Recognition · Computer Science
Learning to generate filters for convolutional neural networks
Wei Shen, Rujie Liu
2018-12-06
Computer Vision and Pattern Recognition · Computer Science
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
Remi Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun +1
2024-03-15
Computer Vision and Pattern Recognition · Computer Science
Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets
Jonghwa Yim, Kyung-Ah Sohn
2017-10-19
Computer Vision and Pattern Recognition · Computer Science
Filter Grafting for Deep Neural Networks
Fanxu Meng, Hao Cheng, Ke Li, Zhixin Xu +3
2020-02-27
Computer Vision and Pattern Recognition · Computer Science
Full-Stack Filters to Build Minimum Viable CNNs
Kai Han, Yunhe Wang, Yixing Xu, Chunjing Xu +2
2019-08-07
Machine Learning · Computer Science
Redundancy in Deep Linear Neural Networks
Oriel BenShmuel
2022-06-10
Computer Vision and Pattern Recognition · Computer Science
Improve Convolutional Neural Network Pruning by Maximizing Filter Variety
Nathan Hubens, Matei Mancas, Bernard Gosselin, Marius Preda +1
2022-03-14
Computer Vision and Pattern Recognition · Computer Science
Improving Efficiency in Convolutional Neural Network with Multilinear Filters
Dat Thanh Tran, Alexandros Iosifidis, Moncef Gabbouj
2018-07-06
Computer Vision and Pattern Recognition · Computer Science
Normalize Filters! Classical Wisdom for Deep Vision
Gustavo Perez, Stella X. Yu
2026-01-16
Computer Vision and Pattern Recognition · Computer Science
Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification
Minho Ha, Younghoon Byeon, Youngjoo Lee, Sunggu Lee
2019-02-15
R2 v1 2026-06-22T14:10:57.457Z