LegoNet: Efficient Convolutional Neural Networks with Lego Filters - PowerPoint PPT Presentation

May 24, 2023 •126 likes •230 views

LegoNet: Efficient Convolutional Neural Networks with Lego Filters Zhaohui Yang 1,2,* Yunhe Wang 2 Han3ng Chen 1,2,* Chuanjian Liu 2 Boxin Shi 3,4 Chao Xu 1 Chunjing Xu 2 Chang Xu 5 1 Laboratory of Machine Percep3on (Ministry of Educa3on), Peking

LegoNet: Efficient Convolutional Neural Networks with Lego Filters Zhaohui Yang 1,2,* Yunhe Wang 2 Han3ng Chen 1,2,* Chuanjian Liu 2 Boxin Shi 3,4 Chao Xu 1 Chunjing Xu 2 Chang Xu 5 1 Laboratory of Machine Percep3on (Ministry of Educa3on), Peking University 2 Huawei Noah’s Ark Lab 3 Peng Cheng Laboratory 4 Na3onal Engineering Laboratory For Video Technology, Peking University 5 School of Computer Science, University of Sydney * This work was down when Zhaohui Yang and Han3ng Chen were interns at Huawei Noah’s Ark Lab
Goal • Mo&va&on Reuse paXerns • Targeted Build efficient CNN using a set of Lego Filters • Lego Filters Standard convolu3on filters are established by a set of shared filters • Op&miza&on End-to-end op3miza3on, Straight Through Es3mator • Efficient Inference Split-Transform-Merge strategy ICML 2019
Lego Filters • Lego Filters B B = {B 1 , …, B m } • Standard convolu&on filters F F = G(B 1 , …, B m ), 4-D tensor G is a genera3on func3on. • Compression condi&on |G| + |B| ≤ |F| • G in LegoNet Combina3on m: the number of Lego Filters B : lego Filters F : standard convolu3on filters G: genera3on func3on ICML 2019
Op&miza&on • Targeted • Op&mize Binary matrix M Float type proxy weight N Straight Through Es3mator (STE) • Op&mize Lego Filters B Standard BP algorithm m: the number of Lego Filters B : Lego Filters M : binary index matrix N : proxy matrix of M ICML 2019
Lego Unit & Efficient Inference • Split • Split input feature maps X • Transform • Convolve feature fragments X = {X 1 , …, X o } with Lego Filters B = {B 1 , …, B m } • Merge • Combine Lego Feature Maps according to learnt combina3on matrix M m: the number of Lego Filters o : split number B : Lego Filters M : binary index matrix ICML 2019
Analysis • Compression • Accelera&on • Condi3on • m ≤ n m: the number of Lego Filters n : the number of output channels o : split number M : binary index matrix ICML 2019
Experiments CIFAR-10 ImageNet Combina3on with coefficients is important while stacking Lego Filters. Given same model size, larger split number o results in higher performance (larger FLOPs) ICML 2019
Conclusion & Future Research • Conclusion • Proposed Lego Filters for construc3ng efficient CNN. • End-to-end op3miza3on. • Split-transform-merge three-stage strategy. • Future Research • Parameter in Parameter (use a set of Lego Filters and a small NN to generate 4-D convolu3on filters) • Global LegoNet (view network parameters as a whole 4-D tensor) ICML 2019
Thanks! ICML 2019

Download Presentation

Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Convolutional Neural Networks ---- Off the shelf top notch performances Convolutional Neural

Transfer Learning with Convolutional Neural Networks ---- Off the shelf top notch performances Convolutional Neural Networks A breakthough Convolutional Neural Networks VGG-16 example Layers of Convolutional filters Bottleneck

625 views • 23 slides

Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN)

Convolutional Kuan-Ting Lai 2020/3/31 Neural Network Convolutional Neural Networks (CNN) A.k.a. CNN or ConvNet Adit Deshpande, A Beginner's Guide To Understanding Convolutional Neural Networks. Digital Images Input array: an images

1.42k views • 72 slides

Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly

Convolutional Neural Nets 4-25-16 Reading Quiz Convolutional neural networks are most commonly used for what sort of task? a) Recognizing images b) Transcribing speech c) Translating documents d) Playing games Neural network review

431 views • 13 slides

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks Neuron Non-linearity Softmax layer DNN training Loss function and regularization SGD and backprop Learning rate Overfitting

1.8k views • 86 slides

Convolutional Neural Networks 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image Processing

Convolutional Neural Networks 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image Processing 2016 Prof. Luiz Velho Convolutional Neural Networks 1 Summary & References 08/11 ImageNet Classification with Deep Convolutional Neural Networks

648 views • 26 slides

MICROBOONE Taritree Wongjirad DPF 2017 Tufts/MIT Outline Convolutional neural networks

Run 3493 Event 41075, Oct. 23rd, 2015 CONVOLUTIONAL NEURAL NETWORKS IN MICROBOONE Taritree Wongjirad DPF 2017 Tufts/MIT Outline Convolutional neural networks (CNNs) are a type of deep, feed-forward neural networks that have been

831 views • 43 slides

Logarithmic Mult ltiplication for Convolutional Neural Networks HyunJin in Kim im, , Min in

A Cost-Efficient It Iterative Truncated Logarithmic Mult ltiplication for Convolutional Neural Networks HyunJin in Kim im, , Min in Soo Kim im, , Alb Alberto A. A. Del l Bar arrio, Nad ader Bag agherzadeh Motivations Well ll

484 views • 11 slides

Convolutional Neural Networks (Part III) 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image

Convolutional Neural Networks (Part III) 08, 10 & 17 Nov, 2016 J. Ezequiel Soto S. Image Processing 2016 Prof. Luiz Velho Convolutional Neural Networks 1 Summary & References 08/11 ImageNet Classification with Deep Convolutional

444 views • 27 slides

Convolutional Neural Networks Rachel Hu and Zhi Zhang Amazon AI d2l.ai Outline GPUs

Convolutional Neural Networks Rachel Hu and Zhi Zhang Amazon AI d2l.ai Outline GPUs Convolutions Pooling, Padding and Stride Convolutional Neural Networks (LeNet) Deep ConvNets (AlexNet) Networks using Blocks (VGG)

1.91k views • 89 slides

Parameter efficient training of deep convolutional neural networks by dynamic sparse

Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization Hesham Mostafa (Intel AI) Xin Wang (Intel AI, Cerebras Systems) Easy : post-training (sparse) compression Hard : direct training of sparse

727 views • 9 slides

Convolutional Neural Networks in Speech Lecture 20 CS 753 Instructor: Preethi Jyothi

Convolutional Neural Networks in Speech Lecture 20 CS 753 Instructor: Preethi Jyothi Convolutional Neural Networks (CNNs) Fully connected (dense) layers have no awareness of spatial information Key concept behind convolutional layers is

983 views • 41 slides

Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) L1 Scalar Processor L0

Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) L1 Scalar Processor L0 L0 M*V Processor N N N N N N Project Brainwave Pretrained DNN Model Scalable DNN Hardware Neural Processing Unit Microservice Extract

525 views • 30 slides

Convolutional Neural Networks Convolutional neural networks One of the major kinds of ANNs in use

Convolutional Neural Networks<br/><br/> 5/4/19, 4(03 PM Convolutional Neural Networks<br/><br/> 5/4/19, 4(03 PM Convolutional Neural Networks Convolutional neural networks One of the major kinds of ANNs in use UMaine

412 views • 9 slides

Dependency-based Convolutional Neural Networks for Sentence Embedding What is Hawaii

Dependency-based Convolutional Neural Networks for Sentence Embedding What is Hawaii s state flower ? ROOT Mingbo Ma Liang Huang Bing Xiang Bowen Zhou CUNY IBM T. J. Watson ACL 2015 Beijing Convolutional Neural Network

742 views • 50 slides

Efficient Neural Networks for Image Restoration Yulun Zhang Supervisor: Prof. Yun Fu SMILE lab,

Efficient Neural Networks for Image Restoration Yulun Zhang Supervisor: Prof. Yun Fu SMILE lab, Northeastern University, Boston, US Research summary Deep convolutional neural networks for Image Restoration 1.Residual dense network. [ CVPR-2018

375 views • 33 slides

Semantic Segmentation of the sekleton in bone scintigraphy images with convolutional neural

Semantic Segmentation of the sekleton in bone scintigraphy images with convolutional neural networks Problem Description Convolutional Neural Networks Convolutional Layer Max Pooling Transforming Classification networks to segmentation

157 views • 12 slides

with Polynomial Filters Josiah Manson and Scott Schaefer Texas A&M University Motivation

Analytic Rasterization of Curves with Polynomial Filters Josiah Manson and Scott Schaefer Texas A&M University Motivation Motivation Motivation Motivation Motivation Motivation Motivation Constant colors Color gradients Motivation

976 views • 70 slides

Filters and Noise Optional Assessment of Practical Importance Rubin H Landau Sally Haerer,

Filters and Noise Optional Assessment of Practical Importance Rubin H Landau Sally Haerer, Producer-Director Based on A Survey of Computational Physics by Landau, Pez, & Bordeianu with Support from the National Science Foundation Course:

378 views • 13 slides

08 Texture Antialiasing Steve Marschner CS5625 Spring 2016 Overview Basic sampling problem

08 Texture Antialiasing Steve Marschner CS5625 Spring 2016 Overview Basic sampling problem Texture mapping defines a signal in image space That signal needs to be filtered: convolved with a filter Approximating this drives all the

1.04k views • 38 slides

Welcome! What is Wrong Here? <?php $sql = " SELECT card_num, card_name, card_expiry

Welcome! What is Wrong Here? <?php $sql = " SELECT card_num, card_name, card_expiry FROM credit_cards WHERE uid = '{$_GET['uid']}' "; ?> http://example.com/script.php?uid=42 SELECT card_num, card_name, card_expiry FROM

556 views • 42 slides

Directed Network Topology Inference via Graph Filter Identification Rasoul Shafipour, Santiago

Directed Network Topology Inference via Graph Filter Identification Rasoul Shafipour, Santiago Segarra , Antonio G. Marques and Gonzalo Mateos Institute for Data, Systems, and Society Massachusetts Institute of Technology segarra@mit.edu

463 views • 30 slides

M emory A ugmented P olicy O ptimization ( MAPO ) for Program Synthesis and Semantic Parsing Chen

M emory A ugmented P olicy O ptimization ( MAPO ) for Program Synthesis and Semantic Parsing Chen Liang, Mohammad Norouzi, Jonathan Berant, Quoc Le, Ni Lao Program Synthesis / Semantic Parsing how many more passengers flew to los angeles than to

686 views • 29 slides

AngularJS Unit Testing AngularJS Filters and Services with Karma & Jasmine Filters

AngularJS Unit Testing AngularJS Filters and Services with Karma & Jasmine Filters Filters can be added in AngularJS to format or transform data AngularJS provides filters to currency - Format a number to a currency format. o date -

147 views • 11 slides

robfilter : An R-Package for Robust Time Series Filters Karen Schettlinger, Roland Fried, Ursula

robfilter : An R-Package for Robust Time Series Filters Karen Schettlinger, Roland Fried, Ursula Gather Fakult at Statistik UseR! The R User Conference 2008, August 12-14, Technische Universit at Dortmund i 1 i 1 Motivation q q

1.74k views • 135 slides