TY - GEN
T1 - Deep fashion recommendation system with style feature decomposition
AU - Shin, Yong Goo
AU - Yeo, Yoon Jae
AU - Sagong, Min Cheol
AU - Ji, Seo Won
AU - Ko, Sung Jea
N1 - Funding Information:
This work was supported by Institute for Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIP) (No. 2019-0-00268, Development of SW technology for recognition, judgement and path control algorithm verification simulation and dataset generation)
Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - Recently, convolutional neural network (CNN) -based fashion recommendation techniques, which automatically recommend the matching clothes to the consumer, have been widely researched. In general, the feature vector of a fashion item, i.e. clothes vector, obtained by CNN conveys two types of information: style and category, where the style indicates the distinctive characteristic of the clothes and the category represents the common properties of the clothes in the same class. Due to the mixed information of style and category, however, the clothes vector often recommends the unmatching clothes. To solve this problem, we propose a style feature extraction (SFE) layer, which effectively decomposes the clothes vector into style and category. Based on the characteristics that the category information has small variations in the same class while being distinguished from other classes, we extract and remove the category information from the clothes vector to obtain more accurate style information. Experimental results show that the proposed method achieves state-of-the-art results in terms of link prediction, which is a performance measure of a stylish match. In addition, as a simple CNN layer, it is expected that the proposed SFE layer is compatible with all popular CNN architectures.
AB - Recently, convolutional neural network (CNN) -based fashion recommendation techniques, which automatically recommend the matching clothes to the consumer, have been widely researched. In general, the feature vector of a fashion item, i.e. clothes vector, obtained by CNN conveys two types of information: style and category, where the style indicates the distinctive characteristic of the clothes and the category represents the common properties of the clothes in the same class. Due to the mixed information of style and category, however, the clothes vector often recommends the unmatching clothes. To solve this problem, we propose a style feature extraction (SFE) layer, which effectively decomposes the clothes vector into style and category. Based on the characteristics that the category information has small variations in the same class while being distinguished from other classes, we extract and remove the category information from the clothes vector to obtain more accurate style information. Experimental results show that the proposed method achieves state-of-the-art results in terms of link prediction, which is a performance measure of a stylish match. In addition, as a simple CNN layer, it is expected that the proposed SFE layer is compatible with all popular CNN architectures.
KW - Convolutional neural network
KW - Deep learning
KW - Recommendation system
KW - Visual compatibility
UR - http://www.scopus.com/inward/record.url?scp=85078943932&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Berlin47944.2019.8966228
DO - 10.1109/ICCE-Berlin47944.2019.8966228
M3 - Conference contribution
AN - SCOPUS:85078943932
T3 - IEEE International Conference on Consumer Electronics - Berlin, ICCE-Berlin
SP - 301
EP - 305
BT - Proceedings - 2019 IEEE 9th International Conference on Consumer Electronics, ICCE-Berlin 2019
A2 - Velikic, Gordan
A2 - Gross, Christian
PB - IEEE Computer Society
T2 - 9th IEEE International Conference on Consumer Electronics, ICCE-Berlin 2019
Y2 - 8 September 2019 through 11 September 2019
ER -