MBS: Macroblock Scaling for CNN Model Reduction

09/18/2018
by   Yu-Hsun Lin, et al.
0

We estimate the proper channel (width) scaling of Convolution Neural Networks (CNNs) for model reduction. Unlike the traditional scaling method that reduces every CNN channel width by the same scaling factor, we address each CNN macroblock adaptively depending on its information redundancy measured by our proposed effective flops. Our proposed macroblock scaling (MBS) algorithm can be applied to various CNN architectures to reduce their model size. These applicable models range from compact CNN models such as MobileNet (25.53 reduction, ImageNet) and ShuffleNet (20.74 ones such as ResNet-101 (51.67 reduction, CIFAR-10) with negligible accuracy degradation. MBS also performs better reduction at a much lower cost than does the state-of-the-art optimization-based method. MBS's simplicity and efficiency, its flexibility to work with any CNN model, and its scalability to work with models of any depth makes it an attractive choice for CNN model size reduction.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/16/2018

Backward Reduction of CNN Models with Information Flow Analysis

This paper proposes backward reduction, an algorithm that explores the c...
research
04/24/2021

Width Transfer: On the (In)variance of Width Optimization

Optimizing the channel counts for different layers of a CNN has shown gr...
research
08/22/2017

Learning Efficient Convolutional Networks through Network Slimming

The deployment of deep convolutional neural networks (CNNs) in many real...
research
11/08/2020

Analysis of Dimensional Influence of Convolutional Neural Networks for Histopathological Cancer Classification

Convolutional Neural Networks can be designed with different levels of c...
research
05/29/2018

A novel channel pruning method for deep neural network compression

In recent years, deep neural networks have achieved great success in the...
research
07/02/2023

A Proximal Algorithm for Network Slimming

As a popular channel pruning method for convolutional neural networks (C...
research
03/11/2021

Fast and Accurate Model Scaling

In this work we analyze strategies for convolutional neural network scal...

Please sign up or login with your details

Forgot password? Click here to reset