Self Similarity Matrix based CNN Filter Pruning

11/03/2022
by   S Rakshith, et al.
0

In recent years, most of the deep learning solutions are targeted to be deployed in mobile devices. This makes the need for development of lightweight models all the more imminent. Another solution is to optimize and prune regular deep learning models. In this paper, we tackle the problem of CNN model pruning with the help of Self-Similarity Matrix (SSM) computed from the 2D CNN filters. We propose two novel algorithms to rank and prune redundant filters which contribute similar activation maps to the output. One of the key features of our method is that there is no need of finetuning after training the model. Both the training and pruning process is completed simultaneously. We benchmark our method on two of the most popular CNN models - ResNet and VGG and record their performance on the CIFAR-10 dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/30/2021

Deep Model Compression based on the Training History

Deep Convolutional Neural Networks (DCNNs) have shown promising results ...
research
04/26/2023

Filter Pruning via Filters Similarity in Consecutive Layers

Filter pruning is widely adopted to compress and accelerate the Convolut...
research
10/27/2022

Efficient Similarity-based Passive Filter Pruning for Compressing CNNs

Convolution neural networks (CNNs) have shown great success in various a...
research
12/10/2021

Network Compression via Central Filter

Neural network pruning has remarkable performance for reducing the compl...
research
07/20/2017

ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression

We propose an efficient and unified framework, namely ThiNet, to simulta...
research
02/26/2022

Symmetric Convolutional Filters: A Novel Way to Constrain Parameters in CNN

We propose a novel technique to constrain parameters in CNN based on sym...
research
06/22/2023

Neural Network Pruning for Real-time Polyp Segmentation

Computer-assisted treatment has emerged as a viable application of medic...

Please sign up or login with your details

Forgot password? Click here to reset