Skip to main navigation Skip to search Skip to main content

Fine-tuning and visualization of convolutional neural networks

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Image classification is a widely discussed topic in the field of computer vision. In recent years, with the application of Convolutional Neural Networks (CNNs), the state-of-the-art in this area has progressed rapidly. To yield a well performed CNN, the advanced GPU and large amount of training data are employed, thus training an entire CNN from scratch is difficult. In practice, fine-tuning a pre-trained CNN is a simple yet effective method to solve a target task. In this paper, we address on the issue of visualizing a fine-tuned CNN, comparing with a small CNN trained from scratch on the same task, to explain how fine-tuning achieve such good performance.

Original languageEnglish
Title of host publicationProceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications, ICIEA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1310-1315
Number of pages6
ISBN (Electronic)9781538621035
DOIs
StatePublished - 2 Jul 2017
Event12th IEEE Conference on Industrial Electronics and Applications, ICIEA 2017 - Siem Reap, Cambodia
Duration: 18 Jun 201720 Jun 2017

Publication series

NameProceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications, ICIEA 2017
Volume2018-February

Conference

Conference12th IEEE Conference on Industrial Electronics and Applications, ICIEA 2017
Country/TerritoryCambodia
CitySiem Reap
Period18/06/1720/06/17

Fingerprint

Dive into the research topics of 'Fine-tuning and visualization of convolutional neural networks'. Together they form a unique fingerprint.

Cite this