TY - GEN
T1 - Semantic segmentation of fashion photos using light-weight asymmetric U-Net
AU - Dang, Anh H.
AU - Kameyama, Wataru
N1 - Funding Information:
This research is supported by funding from Leafnet Co., Ltd. in Japan.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Semantic segmentation is crucial for machine image understanding. The availability of public data set such as MSCOCO, ADE20K and CityScape encourages the development of popular models for semantic segmentation like SegNet and PSPNet. In this paper, we propose a light-weight deep neural network for street-fashion semantic segmentation. Experiment on ModaNet data set shows that our proposed network results in high accuracy despite its low requirement in the computational resource.
AB - Semantic segmentation is crucial for machine image understanding. The availability of public data set such as MSCOCO, ADE20K and CityScape encourages the development of popular models for semantic segmentation like SegNet and PSPNet. In this paper, we propose a light-weight deep neural network for street-fashion semantic segmentation. Experiment on ModaNet data set shows that our proposed network results in high accuracy despite its low requirement in the computational resource.
KW - Fashion photos
KW - ModaNet
KW - Semantic segmentation
KW - Street-fashion
KW - U-Net
UR - http://www.scopus.com/inward/record.url?scp=85081964310&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081964310&partnerID=8YFLogxK
U2 - 10.1109/GCCE46687.2019.9015571
DO - 10.1109/GCCE46687.2019.9015571
M3 - Conference contribution
AN - SCOPUS:85081964310
T3 - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
SP - 175
EP - 178
BT - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th IEEE Global Conference on Consumer Electronics, GCCE 2019
Y2 - 15 October 2019 through 18 October 2019
ER -