CASIA OpenIR  > 智能系统与工程
Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping
Li, Debang1,2; Wu, Huikai1,2; Zhang, Junge1,2; Huang, Kaiqi1,2,3
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149
2019-10-01
卷号28期号:10页码:5105-5120
摘要

Image cropping aims at improving the quality of images by removing unwanted outer areas, which is widely used in the photography and printing industry. Most of the previous cropping methods that do not need bounding box supervision rely on the sliding window mechanism. The sliding window method results in fixed aspect ratios and limits the shape of the cropping region. Moreover, the sliding window method usually produces lots of candidates on the input image, which is very time-consuming. Motivated by these challenges, we formulate image cropping as a sequential decision-making process and propose a reinforcement learning-based framework to address this problem, namely, Fast Aesthetics-Aware Adversarial Reinforcement Learning (Fast A3RL). Particularly, the proposed method develops an aesthetics-aware reward function that is dedicated for image cropping. Similar to human's decision-making process, we use a comprehensive state representation, including both the current observation and the historical experience. We train the agent using the actor-critic architecture in an end-to-end manner. The adversarial learning process is also applied during the training stage. The proposed method is evaluated on several popular cropping datasets, in which the images are unseen during training. The experiment results show that our method achieves the state-of-the-art performance with much fewer candidate windows and much less time compared with related methods.

关键词Reinforcement learning adversarial learning image cropping
DOI10.1109/TIP.2019.2914360
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[61876181] ; Projects of Chinese Academy of Sciences[QYZDB-SSW-JSC006] ; National Key Research and Development Program of China[2016YFB1001004] ; National Natural Science Foundation of China[61673375] ; National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61721004] ; National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61673375] ; National Key Research and Development Program of China[2016YFB1001004] ; Projects of Chinese Academy of Sciences[QYZDB-SSW-JSC006] ; National Natural Science Foundation of China[61876181]
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000482599100009
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类图像视频处理与分析
引用统计
被引频次:25[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/27336
专题智能系统与工程
通讯作者Huang, Kaiqi
作者单位1.CRISE, Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
3.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Li, Debang,Wu, Huikai,Zhang, Junge,et al. Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2019,28(10):5105-5120.
APA Li, Debang,Wu, Huikai,Zhang, Junge,&Huang, Kaiqi.(2019).Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping.IEEE TRANSACTIONS ON IMAGE PROCESSING,28(10),5105-5120.
MLA Li, Debang,et al."Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping".IEEE TRANSACTIONS ON IMAGE PROCESSING 28.10(2019):5105-5120.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
08708941.pdf(6588KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li, Debang]的文章
[Wu, Huikai]的文章
[Zhang, Junge]的文章
百度学术
百度学术中相似的文章
[Li, Debang]的文章
[Wu, Huikai]的文章
[Zhang, Junge]的文章
必应学术
必应学术中相似的文章
[Li, Debang]的文章
[Wu, Huikai]的文章
[Zhang, Junge]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 08708941.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。