Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 신경식 | * |
dc.date.accessioned | 2018-12-03T16:30:10Z | - |
dc.date.available | 2018-12-03T16:30:10Z | - |
dc.date.issued | 2018 | * |
dc.identifier.isbn | 9781538647936 | * |
dc.identifier.other | OAK-23902 | * |
dc.identifier.uri | https://dspace.ewha.ac.kr/handle/2015.oak/247172 | - |
dc.description.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%. © 2018 IEEE. | * |
dc.language | English | * |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | * |
dc.subject | Convolutional Neural Network | * |
dc.subject | fashion image | * |
dc.subject | fine-grained classification | * |
dc.subject | pre-trained network | * |
dc.title | Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network | * |
dc.type | Conference Paper | * |
dc.relation.index | SCOPUS | * |
dc.relation.startpage | 387 | * |
dc.relation.lastpage | 390 | * |
dc.relation.journaltitle | 2018 IEEE 3rd International Conference on Big Data Analysis, ICBDA 2018 | * |
dc.identifier.doi | 10.1109/ICBDA.2018.8367713 | * |
dc.identifier.scopusid | 2-s2.0-85048490367 | * |
dc.author.google | Seo Y. | * |
dc.author.google | Shin K.-S. | * |
dc.contributor.scopusid | 신경식(56927436200) | * |
dc.date.modifydate | 20240118131805 | * |