|
JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/17587
|
| Title: | Model Diet: A Simple yet Effective Model Compression for Vision Tasks |
| Authors: | Lee, Jongmin
Elibol, Armagan
Chong, Nak-Young |
| Keywords: | computer vision
deep neural networks
involution
filter pruning
model compression |
| Issue Date: | 2021-10 |
| Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
| Magazine name: | 2021 21st International Conference on Control, Automation and Systems (ICCAS 2021) |
| Start page: | 506 |
| End page: | 511 |
| DOI: | 10.23919/ICCAS52745.2021.9649988 |
| Abstract: | Computer vision coupled with machine learning algorithms has greatly helped mobile robotic platforms become more intelligent and capable of performing in the real world. Specifically, Convolutional Neural Networks (CNNs) have achieved a high accuracy on a range of visual perception tasks (e.g., object detection, classification, segmentation, and similar others). One of the bottlenecks in CNNs is their high computational requirement. This makes most of them not easily deployable on robotic platforms, since their on-board computational power is limited. Recently, Involution successfully reduced the number of parameters of CNNs by replacing all the 3 × 3 convolution kernels with involution kernels, which use 1 × 1 convolution for the kernel generation. Filter pruning methods have also successively reduced the number of parameters in CNNs. Notably, however, Involution has reshaping layers and the kernel size is unknown when loading the pre-trained model. In this paper, we propose a pruning method named Model Diet that can be applied to Involution and other CNNs. We present experimental results showing that it has better results compared with randomly initialized weights. |
| Rights: | This is the author's version of the work. Copyright (C) 2021 IEEE. 2021 21st International Conference on Control, Automation and Systems (ICCAS 2021), 2021, pp.506-511. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| URI: | http://hdl.handle.net/10119/17587 |
| Material Type: | author |
| Appears in Collections: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| ICCAS_2021_ Jongmin.pdf | | 334Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
