Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping
文献类型：期刊论文
| 作者 | Li, Debang1,2 ; Wu, Huikai1,2; Zhang, Junge1,2; Huang, Kaiqi1,2,3
|
| 刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
 |
| 出版日期 | 2019-10-01 |
| 卷号 | 28期号:10页码:5105-5120 |
| 关键词 | Reinforcement learning adversarial learning image cropping |
| ISSN号 | 1057-7149 |
| DOI | 10.1109/TIP.2019.2914360 |
| 通讯作者 | Huang, Kaiqi(kqhuang@nlpr.ia.ac.cn) |
| 英文摘要 | 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. |
| 资助项目 | National Key Research and Development Program of China[2016YFB1001004] ; National Key Research and Development Program of China[2016YFB1001005] ; National Natural Science Foundation of China[61876181] ; National Natural Science Foundation of China[61673375] ; National Natural Science Foundation of China[61721004] ; Projects of Chinese Academy of Sciences[QYZDB-SSW-JSC006] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000482599100009 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Projects of Chinese Academy of Sciences |
| 源URL | [http://ir.ia.ac.cn/handle/173211/27335]  |
| 专题 | 智能系统与工程 |
| 通讯作者 | Huang, Kaiqi |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China |
| 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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。