Consensus-Agent Deep Reinforcement Learning for Face Aging

doi:10.1109/TIP.2024.3364074

CSpace

	Consensus-Agent Deep Reinforcement Learning for Face Aging
	Lin, Ling 1,2; Liu, Hao 1,2; Liang, Jinqiao 1,2; Li, Zhendong 1,2; Feng, Jiao 3; Han, Hu 4,5
	2024
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	33 页码:1795-1809
摘要	Face aging tasks aim to simulate changes in the appearance of faces over time. However, due to the lack of data on different ages under the same identity, existing models are commonly trained using mapping between age groups. This makes it difficult for most existing aging methods to accurately capture the correspondence between individual identities and aging features, leading to generating faces that do not match the real aging appearance. In this paper, we re-annotate the CACD2000 dataset and propose a consensus-agent deep reinforcement learning method to solve the aforementioned problem. Specifically, we define two agents, the aging process agent and the aging personalization agent, and model the task of matching aging features as a Markov decision process. The aging process agent simulates the aging process of an individual, while the aging personalization agent calculates the difference between the aging appearance of an individual and the average aging appearance. The two agents iteratively adjust the matching degree between the target aging feature and the current identity through a form of synergistic cooperation. Extensive experimental results on four face aging datasets show that our model achieves convincing performance compared to the current state-of-the-art methods.
关键词	Face aging deep reinforcement learning Markov decision process
DOI	10.1109/TIP.2024.3364074
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001184885100006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38741
专题	中国科学院计算技术研究所
通讯作者	Liu, Hao
作者单位	1.Ningxia Univ, Sch Informat Engn, Yinchuan 750021, Peoples R China 2.Ningxia Key Lab Artificial Intelligence & Informat, Yinchuan 750021, Peoples R China 3.Ningxia Univ, Sch Innovat & Entrepreneurship, Yinchuan 750021, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 5.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Lin, Ling,Liu, Hao,Liang, Jinqiao,et al. Consensus-Agent Deep Reinforcement Learning for Face Aging[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:1795-1809.
APA	Lin, Ling,Liu, Hao,Liang, Jinqiao,Li, Zhendong,Feng, Jiao,&Han, Hu.(2024).Consensus-Agent Deep Reinforcement Learning for Face Aging.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,1795-1809.
MLA	Lin, Ling,et al."Consensus-Agent Deep Reinforcement Learning for Face Aging".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):1795-1809.