Knowledge Commons of Institute of Automation,CAS
A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping | |
Li, Debang1,2![]() ![]() ![]() ![]() | |
2018-06 | |
会议名称 | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018 |
会议录名称 | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018 |
页码 | 8193-8201 |
会议日期 | 18-23 June 2018 |
会议地点 | Salt Lake City, UT, USA |
会议录编者/会议主办者 | IEEE ; CVF |
出版者 | IEEE |
摘要 | Image cropping aims at improving the aesthetic quality of images by adjusting their composition. Most weakly supervised cropping methods (without bounding box supervision) rely on the sliding window mechanism. The sliding window mechanism requires fixed aspect ratios and limits the cropping region with arbitrary size. Moreover, the sliding window method usually produces tens of thousands of windows on the input image which is very time-consuming. Motivated by these challenges, we firstly formulate the aesthetic image cropping as a sequential decision-making process and propose a weakly supervised Aesthetics Aware Reinforcement Learning (A2-RL) framework to address this problem. Particularly, the proposed method develops an aesthetics aware reward function which especially benefits image cropping. Similar to human's decision making, 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 agent is evaluated on several popular unseen cropping datasets. Experiment results show that our method achieves the state-of-the-art performance with much fewer candidate windows and much less time compared with previous weakly supervised methods. |
URL | 查看原文 |
收录类别 | EI |
资助项目 | Chinese Academy of Science[173211KYSB20160008] ; Chinese Academy of Science[QYZDB-SSW-JSC006] ; National Natural Science Foundation of China[61403383] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[61673375] ; National Key Research and Development Program of China[2016YFB1001005] ; National Key Research and Development Program of China[2016YFB1001004] |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44362 |
专题 | 复杂系统认知与决策实验室_智能系统与工程 |
通讯作者 | Huang, Kaiqi |
作者单位 | 1.CRIPAC & NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China 3.University of Chinese Academy of Sciences, Beijing, China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Li, Debang,Wu, Huikai,Zhang, Junge,et al. A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping[C]//IEEE, CVF:IEEE,2018:8193-8201. |
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 | ||
08578953.pdf(750KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论