Fast A3RL: Aesthetics-Aware Adversarial Reinforcement Learning for Image Cropping

对抗制 深度学习 人工神经网络 嵌入 卷积神经网络
作者
Debang Li,Huikai Wu,Junge Zhang,Kaiqi Huang
出处
期刊:IEEE Transactions on Image Processing 卷期号:28 (10): 5105-5120 被引量:14
标识
DOI:10.1109/tip.2019.2914360
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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
CipherSage应助友好驳采纳,获得10
刚刚
1秒前
MUAN完成签到 ,获得积分10
1秒前
3秒前
daxiong发布了新的文献求助10
4秒前
哈哈哈完成签到,获得积分10
4秒前
4秒前
5秒前
学习使我快乐完成签到 ,获得积分10
6秒前
simon完成签到,获得积分10
6秒前
wuhuofeng发布了新的文献求助10
6秒前
我想当二郎神完成签到,获得积分10
7秒前
9秒前
友好驳完成签到,获得积分10
12秒前
la完成签到,获得积分10
12秒前
12秒前
zhiwei完成签到 ,获得积分0
14秒前
初之发布了新的文献求助20
17秒前
猪猪hero发布了新的文献求助10
17秒前
18秒前
wuhuofeng完成签到,获得积分10
19秒前
19秒前
York Chang完成签到,获得积分10
19秒前
丫头发布了新的文献求助10
19秒前
19秒前
21秒前
王者归来发布了新的文献求助200
23秒前
伊星儿发布了新的文献求助10
23秒前
阿朱关注了科研通微信公众号
23秒前
24秒前
大模型应助zsy采纳,获得10
24秒前
初之完成签到,获得积分20
25秒前
猪猪hero发布了新的文献求助10
26秒前
mt13发布了新的文献求助10
28秒前
上官若男应助是江江哥啊采纳,获得10
29秒前
30秒前
30秒前
Rondab应助zhangtengteng采纳,获得10
31秒前
32秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3975426
求助须知:如何正确求助?哪些是违规求助? 3519848
关于积分的说明 11199831
捐赠科研通 3256122
什么是DOI,文献DOI怎么找? 1798124
邀请新用户注册赠送积分活动 877386
科研通“疑难数据库(出版商)”最低求助积分说明 806305