ZipNet: ZFNet-level accuracy with 48× fewer parameters

College

College of Computer Studies

Department/Unit

Software Technology

Document Type

Conference Proceeding

Source Title

VCIP 2018 - IEEE International Conference on Visual Communications and Image Processing

Publication Date

7-2-2018

Abstract

With the introduction of Convolutional Neural Networks, models for image classification achieve higher classification accuracy. Based on the pattern of the design of CNN architectures, increasing the number of layers equates to a higher classification accuracy, but also increases the number of parameters and model size. This negatively affects the model training time, processing time, and memory requirement. We develop ZipNet, a CNN architecture with a higher classification accuracy than ZFNet, the winner of ILSVRC 2013, but with 48.5× smaller model size and 48.7× fewer parameters. The classification accuracy of ZipNet is higher than the performance of ZFNet and SqueezeNet on all configurations of the Caltech-256 dataset with varying number of training examples. © 2018 IEEE.

html

Digitial Object Identifier (DOI)

10.1109/VCIP.2018.8698672

Disciplines

Computer Sciences

Keywords

Neural networks (Computer science); Image converters; Visual communication

Upload File

wf_no

This document is currently not available here.

Share

COinS