Effective Data Augmentation with Multi-Domain Learning GANs

被引:0
|
作者
Yamaguchi, Shin'ya [1 ]
Kanai, Sekitoshi [1 ,2 ]
Eda, Takeharu [1 ]
机构
[1] NTT Software Innovat Ctr, Tokyo, Japan
[2] Keio Univ, Tokyo, Japan
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
For deep learning applications, the massive data development (e.g., collecting, labeling), which is an essential process in building practical applications, still incurs seriously high costs. In this work, we propose an effective data augmentation method based on generative adversarial networks (GANs), called Domain Fusion. Our key idea is to import the knowledge contained in an outer dataset to a target model by using a multi-domain learning GAN. The multi-domain learning GAN simultaneously learns the outer and target dataset and generates new samples for the target tasks. The simultaneous learning process makes GANs generate the target samples with high fidelity and variety. As a result, we can obtain accurate models for the target tasks by using these generated samples even if we only have an extremely low volume target dataset. We experimentally evaluate the advantages of Domain Fusion in image classification tasks on 3 target datasets: CIFAR-100, FGVC-Aircraft, and Indoor Scene Recognition. When trained on each target dataset reduced the samples to 5,000 images, Domain Fusion achieves better classification accuracy than the data augmentation using fine-tuned GANs. Furthermore, we show that Domain Fusion improves the quality of generated samples, and the improvements can contribute to higher accuracy.
引用
收藏
页码:6566 / 6574
页数:9
相关论文
共 50 条
  • [21] Multi-Domain Generalized Graph Meta Learning
    Lin, Mingkai
    Li, Wenzhong
    Li, Ding
    Chen, Yizhou
    Li, Guohao
    Lu, Sanglu
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4, 2023, : 4479 - 4487
  • [22] Effective Elasticity for Data Centers Interconnection in Multi-Domain WAN: Information Modelling and Routing
    Iovanna, Paola
    Ubaldi, Fabio
    Giurlanda, Francesco
    Noto, Sandro
    Priola, Alessandro
    Contreras, Luis M.
    Lopez, Victor
    Gimenez, Juan Pedro Fernandez-Palacios
    [J]. ECOC 2015 41ST EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION, 2015,
  • [23] Collaborative Learning in Multi-Domain Optical Networks
    Chen, Xiaoliang
    Proietti, Roberto
    Liu, Che-Yu
    Ben Yoo, S. J.
    [J]. 2020 ASIA COMMUNICATIONS AND PHOTONICS CONFERENCE (ACP) AND INTERNATIONAL CONFERENCE ON INFORMATION PHOTONICS AND OPTICAL COMMUNICATIONS (IPOC), 2020,
  • [24] MADELYN: Multi-Domain Multi-Agent Reinforcement Learning for Data-center Networks
    Kattepur, Ajay
    David, Sushanth
    [J]. 2022 IEEE 46TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE (COMPSAC 2022), 2022, : 624 - 629
  • [25] Unsupervised multi-domain image translation with domain representation learning
    Liu, Huajun
    Chen, Lei
    Sui, Haigang
    Zhu, Qing
    Lei, Dian
    Liu, Shubo
    [J]. SIGNAL PROCESSING-IMAGE COMMUNICATION, 2021, 99
  • [26] Multi-Domain Sequential Recommendation via Domain Space Learning
    Hwang, Junyoung
    Ju, Hyunjun
    Kang, SeongKu
    Jang, Sanghwan
    Yu, Hwanjo
    [J]. PROCEEDINGS OF THE 47TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2024, 2024, : 2134 - 2144
  • [27] Towards Efficient Multi-domain Data Processing
    Luong, Johannes
    Habich, Dirk
    Kissinger, Thomas
    Lehner, Wolfgang
    [J]. DATA MANAGEMENT TECHNOLOGIES AND APPLICATIONS, 2017, 737 : 47 - 64
  • [28] Multi-Domain Data Integration for Criminal Intelligence
    Dajda, Jacek
    Debski, Roman
    Kisiel-Dorohinicki, Marek
    Pietak, Kamil
    [J]. MAN-MACHINE INTERACTIONS 3, 2014, 242 : 345 - 352
  • [29] Data Fabrics for Multi-Domain Information Systems
    Habibi, Pooyan
    Moghaddassian, Morteza
    Shafaghi, Shayan
    Leon-Garcia, Alberto
    [J]. 2023 19TH INTERNATIONAL CONFERENCE ON NETWORK AND SERVICE MANAGEMENT, CNSM, 2023,
  • [30] Quality Multi-domain Meshing for Volumetric Data
    Zhang, Qin
    Subramanian, Bharadwaj
    Xu, Guoliang
    Bajaj, Chandrajit L.
    [J]. 2010 3RD INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING AND INFORMATICS (BMEI 2010), VOLS 1-7, 2010, : 472 - 476