View : 682 Download: 0
Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network
- Title
- Image classification of fine-grained fashion image based on style using pre-trained convolutional neural network
- Authors
- Seo Y.; Shin K.-S.
- Ewha Authors
- 신경식
- SCOPUS Author ID
- 신경식
- Issue Date
- 2018
- Journal Title
- 2018 IEEE 3rd International Conference on Big Data Analysis, ICBDA 2018
- Citation
- 2018 IEEE 3rd International Conference on Big Data Analysis, ICBDA 2018, pp. 387 - 390
- Keywords
- Convolutional Neural Network; fashion image; fine-grained classification; pre-trained network
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Indexed
- SCOPUS
- Document Type
- Conference Paper
- 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.
- DOI
- 10.1109/ICBDA.2018.8367713
- ISBN
- 9781538647936
- Appears in Collections:
- 경영대학 > 경영학전공 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML