Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network

Yian Seo, Kyung Shik Shin

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

25 Scopus citations

Abstract

Deep learning has emerged as a new methodology with continuous interests in artificial intelligence, and it can be applied in various business fields for better performance. In fashion business, deep learning, especially Convolutional Neural Network (CNN), is used in classification of apparel image. However, apparel classification can be difficult due to various apparel categories and lack of labeled image data for each category. Therefore, we propose to pre-train the GoogLeNet architecture on ImageNet dataset and fine-tune on our fine-grained fashion dataset based on design attributes. This will complement the small size of dataset and reduce the training time. After 10-fold experiments, the average final test accuracy results 62%.

Original languageEnglish
Title of host publication2018 IEEE 3rd International Conference on Big Data Analysis, ICBDA 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages387-390
Number of pages4
ISBN (Electronic)9781538647936
DOIs
StatePublished - 25 May 2018
Event3rd IEEE International Conference on Big Data Analysis, ICBDA 2018 - Shanghai, China
Duration: 9 Mar 201812 Mar 2018

Publication series

Name2018 IEEE 3rd International Conference on Big Data Analysis, ICBDA 2018

Conference

Conference3rd IEEE International Conference on Big Data Analysis, ICBDA 2018
Country/TerritoryChina
CityShanghai
Period9/03/1812/03/18

Keywords

  • Convolutional Neural Network
  • fashion image
  • fine-grained classification
  • pre-trained network

Fingerprint

Dive into the research topics of 'Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network'. Together they form a unique fingerprint.

Cite this