Improving Image Aesthetic Assessment via Multiple Image Joint Learning

Author:

Shi Tengfei1ORCID,Chen Chenglizhao2ORCID,Wu Zhenyu3ORCID,Hao Aimin4ORCID,Fang Yuming5ORCID

Affiliation:

1. School of Computer Engineering, Hubei University of Arts and Science; State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, CN

2. Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), CN

3. Southwest Jiaotong University, CN

4. State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, CN

5. Jiangxi University of Finance and Economics, CN

Abstract

I mage A esthetic A ssessment (IAA) is an emerging paradigm that predicts aesthetic score as the popular aesthetic taste for an image. Previous IAA approaches take a single image as input to predict the aesthetic score of the image. However, we discover that most existing IAA methods fail dramaticlly to predict the images with large variance of aesthetic voting distribution. Motivated by the practice that people considers similar experiences to improve the consistence of the voting result, we present a novel M ultiple I mage joint L earning Net work (MILNet) to mimic this natural process. Our novelty is mainly three-fold: (a) Semantic-based retrieval method that constructs aesthetic similarity (the similarity of aesthetic attribution) to select reference images; (b) Graph network reasoning that initializes and updates the weight of intrinsic relationships among multiple images; (c) Adaptive Earth Mover’s Distance (AdaEMD) loss function that adjusts weight for easy and hard instances to mitigate unbalanced distribution of aesthetic datasets. Our evaluation with the benchmark AVA and TAD datasets demonstrates that the proposed MILNet outperforms state-of-the-art IAA methods. The code is available at https://github.com/flyingbird93/MILNet .

Publisher

Association for Computing Machinery (ACM)

Reference60 articles.

1. Qiuyu Chen, Wei Zhang, Ning Zhou, Peng Lei, Yi Xu, Yu Zheng, and Jianping Fan. 2020. Adaptive fractional dilated convolution network for image aesthetics assessment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14114–14123.

2. Yunpeng Chen, Marcus Rohrbach, Zhicheng Yan, Yan Shuicheng, Jiashi Feng, and Yannis Kalantidis. 2019. Graph-based global reasoning networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 433–442.

3. Matching Faces and Attributes Between the Artistic and the Real Domain: the PersonArt Approach

4. Social-sensed image aesthetics assessment;Cui Chaoran;ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM),2020

5. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 248–255.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3