Knowledge Commons of Institute of Automation,CAS
ScoreMix: A Scalable Augmentation Strategy for Training GANs With Limited Data | |
Cao, Jie1,2,3; Luo, Mandi1,2,3; Yu, Junchi1,2,3; Yang, Ming-Hsuan4; He, Ran1,2,3 | |
发表期刊 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE |
ISSN | 0162-8828 |
2023-07-01 | |
卷号 | 45期号:7页码:8920-8935 |
文章类型 | 原创研究 |
摘要 | Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-specific augmentation techniques. Despite the effectiveness, it is difficult for these methods to scale to practical applications. In this article, we present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks. We first produce augmented samples using the convex combinations of the real samples. Then, we optimize the augmented samples by minimizing the norms of the data scores, i.e., the gradients of the log-density functions. This procedure enforces the augmented samples close to the data manifold. To estimate the scores, we train a deep estimation network with multi-scale score matching. For different image synthesis tasks, we train the score estimation network using different data. We do not require the tuning of the hyperparameters or modifications to the network architecture. The ScoreMix method effectively increases the diversity of data and reduces the overfitting problem. Moreover, it can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ScoreMix method achieve significant improvements. |
关键词 | Generative adversarial networks image synthesis data augmentation few-shot image-to-image translation |
DOI | 10.1109/TPAMI.2022.3231649 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[6220073425] ; National Natural Science Foundation of China[U21B2045] ; National Natural Science Foundation of China[U20A20223] ; NSF CAREER[1149783] |
项目资助者 | National Natural Science Foundation of China ; NSF CAREER |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:001004665900065 |
出版者 | IEEE COMPUTER SOC |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 人工智能基础理论 |
国重实验室规划方向分类 | 多尺度信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/53631 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | He, Ran |
作者单位 | 1.Chinese Acad Sci, Inst Automat, CRIPAC, Beijing 100045, Peoples R China 2.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100045, Peoples R China 3.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 4.Univ Calif Merced, Merced, CA 95343 USA |
第一作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
通讯作者单位 | 中国科学院自动化研究所; 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Cao, Jie,Luo, Mandi,Yu, Junchi,et al. ScoreMix: A Scalable Augmentation Strategy for Training GANs With Limited Data[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(7):8920-8935. |
APA | Cao, Jie,Luo, Mandi,Yu, Junchi,Yang, Ming-Hsuan,&He, Ran.(2023).ScoreMix: A Scalable Augmentation Strategy for Training GANs With Limited Data.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(7),8920-8935. |
MLA | Cao, Jie,et al."ScoreMix: A Scalable Augmentation Strategy for Training GANs With Limited Data".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.7(2023):8920-8935. |
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 | ||
Cao 等 - 2023 - Score(1823KB) | 期刊论文 | 作者接受稿 | 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