TY - GEN
T1 - PAC-Net
T2 - 25th IEEE International Conference on Image Processing, ICIP 2018
AU - Ko, Keunsoo
AU - Lee, Jun Tae
AU - Kim, Chang-Su
N1 - Funding Information:
This work was supported in part by the National Research Foundation of Korea (NRF) through the Korea Government (MSIP) (No. NRF-2015R1A2A1A10055037), and in part by the Ministry of Science and ICT (MSIT), Korea, under the Information Technology Research Center support program (IITP-2018-2016-0-00464) supervised by the Institute for Information & Communications Technology Promotion.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/8/29
Y1 - 2018/8/29
N2 - Image aesthetic assessment is important for finding well taken and appealing photographs but is challenging due to the ambiguity and subjectivity of aesthetic criteria. We develop the pairwise aesthetic comparison network (PAC-Net), which consists of two parts: aesthetic feature extraction and pairwise feature comparison. To alleviate the ambiguity and subjectivity, we train PAC-Net to learn the relative aesthetic ranks of two images by employing a novel loss function, called aesthetic-adaptive cross entropy loss. Then, we develop simple schemes for using PAC-Net in the tasks of aesthetic ranking and aesthetic classification, respectively. Experimental results demonstrate that PAC-Net achieves the state-of-the-art performances in both the ranking and classification applications.
AB - Image aesthetic assessment is important for finding well taken and appealing photographs but is challenging due to the ambiguity and subjectivity of aesthetic criteria. We develop the pairwise aesthetic comparison network (PAC-Net), which consists of two parts: aesthetic feature extraction and pairwise feature comparison. To alleviate the ambiguity and subjectivity, we train PAC-Net to learn the relative aesthetic ranks of two images by employing a novel loss function, called aesthetic-adaptive cross entropy loss. Then, we develop simple schemes for using PAC-Net in the tasks of aesthetic ranking and aesthetic classification, respectively. Experimental results demonstrate that PAC-Net achieves the state-of-the-art performances in both the ranking and classification applications.
KW - Aesthetic ranking
KW - And pairwise comparison
KW - Convolutional neural networks
KW - Image aesthetic assessment
UR - http://www.scopus.com/inward/record.url?scp=85062908586&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2018.8451621
DO - 10.1109/ICIP.2018.8451621
M3 - Conference contribution
AN - SCOPUS:85062908586
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2491
EP - 2495
BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PB - IEEE Computer Society
Y2 - 7 October 2018 through 10 October 2018
ER -