Flexi-Compression: A Flexible Model Compression Method for Autonomous Driving

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.

Creator: 

Liu, Hantao

Date: 

2021

Abstract: 

Benefiting from the rapid development of convolutional neural networks, computer vision-based autonomous driving technologies are gradually being deployed in vehicles. However, these neural networks typically have a large number of parameters and extremely high computational costs, making them difficult to deploy in autonomous vehicles with limited storage and computational power. In this paper, we propose an innovative model compression approach to compress convolutional neural networks in autonomous driving algorithms, which we call Flexi-Compression. Flexi-Compression first modifies the model structure by replacing the traditional convolutional layers with our proposed Flexi-CP module, thus reducing the computation of the convolutional layers. Then, we leverage knowledge distillation to enable the compressed model to quickly acquire the knowledge of the original model. In addition, we use a Flexi-Batch Normalization layer to prune the model and finally further reduce the model size by model quantization. We compress an autonomous driving algorithm and achieve excellent performance.

Subject: 

Artificial Intelligence
Engineering - Automotive
Industrial

Language: 

English

Publisher: 

Carleton University

Thesis Degree Name: 

Master of Information Technology: 
M.I.T.

Thesis Degree Level: 

Master's

Thesis Degree Discipline: 

Network Technology

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).