TY - GEN
T1 - Transfer Learning using Transformation
T2 - 11th International Conference on Information and Communication Technology Convergence, ICTC 2020
AU - Lim, Heejeong
AU - Yoon, Seongwook
AU - Sull, Sanghoon
N1 - Funding Information:
”This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2016-0-00464) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation)“
Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/21
Y1 - 2020/10/21
N2 - We propose a simple method of transfer learning for image segmentation. Creating labeled data for deep neural network training in image segmentation is particularly expensive than other tasks. Hence, practically, the labeled data is much less than the unlabeled data. So, we introduce a method that is helpful for segmentation by using unlabeled data. Our key is the RGB-to-HSV transformation and we use it in two ways. The first way is to pre-train a network to work as an RGB-to-HSV transformer which can extract useful features, and transfer the pre-trained weights to another network for segmentation, which is one of the most common transfer learning method. The second way is to provide additional information to the segmented network by providing HSV, the output of the pre-trained network, as additional input. We performed several experiments about our proposal using Cityscapes dataset.
AB - We propose a simple method of transfer learning for image segmentation. Creating labeled data for deep neural network training in image segmentation is particularly expensive than other tasks. Hence, practically, the labeled data is much less than the unlabeled data. So, we introduce a method that is helpful for segmentation by using unlabeled data. Our key is the RGB-to-HSV transformation and we use it in two ways. The first way is to pre-train a network to work as an RGB-to-HSV transformer which can extract useful features, and transfer the pre-trained weights to another network for segmentation, which is one of the most common transfer learning method. The second way is to provide additional information to the segmented network by providing HSV, the output of the pre-trained network, as additional input. We performed several experiments about our proposal using Cityscapes dataset.
KW - HSV transformation
KW - Image segmentation
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85098958122&partnerID=8YFLogxK
U2 - 10.1109/ICTC49870.2020.9289267
DO - 10.1109/ICTC49870.2020.9289267
M3 - Conference contribution
AN - SCOPUS:85098958122
T3 - International Conference on ICT Convergence
SP - 387
EP - 390
BT - ICTC 2020 - 11th International Conference on ICT Convergence
PB - IEEE Computer Society
Y2 - 21 October 2020 through 23 October 2020
ER -