Learning Convolutional Neural Network Using Data from Other Domains in case of Insufficient Data

被引:4
|
作者
Ha, Jeonghyo [1 ]
Eun, Jung [1 ]
Ahn, Pyunghwan [1 ]
Shin, Dong Hoon [2 ]
Kim, Junmo [1 ]
机构
[1] Korea Adv Inst Sci & Technol, Daejeon, South Korea
[2] KINAC, Daejeon, South Korea
关键词
Neural Network; Siamese Network; Multi-domain Data; Image;
D O I
10.1145/3209914.3209927
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we describe a training methodology of convolutional neural networks(CNNs) using data from a different domain when the number of training data in the test domain is small. Training a CNN for classification without enough data might lead to serious problems of overfitting and thus fail to generalize. In this case, if large data of the same object categories is available in another domain, this problem can be alleviated. We propose a method to train a CNN with small data in the test domain and large data in another. Since training a single network using data from different domains could lead to performance degradation, we consider this problem as cross-domain image similarity learning. In our experiment, we train a Siamese network to compute similarity between a pair of images from different domains, which are natural photos and 3D model projections. We design the network to output the probability that the input image pair belongs to the same category. Thus, the network can calculate similarity between the input pair and also classify a natural photo by comparing it with each images in the 3D model database. Since the network output represents similarity, we can greatly reduce testing time for classification compared to other methods (such as NN classification) in which distances between feature vectors must be calculated for every pair of images.
引用
收藏
页码:122 / 126
页数:5
相关论文
共 50 条
  • [1] Convolutional neural network learning for generic data classification
    Han, Huimei
    Li, Ying
    Zhu, Xingquan
    [J]. INFORMATION SCIENCES, 2019, 477 : 448 - 465
  • [2] Learning Cognitive Features from Gaze Data for Sentiment and Sarcasm Classification using Convolutional Neural Network
    Mishra, Abhijit
    Dey, Kuntal
    Bhattacharyya, Pushpak
    [J]. PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1, 2017, : 377 - 387
  • [3] Functional data learning using convolutional neural networks
    Galarza, J.
    Oraby, T.
    [J]. MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2024, 5 (01):
  • [4] Paper: Extraction of Guardrails from MMS Data Using Convolutional Neural Network
    Matsumoto, Hiroki
    Mori, Yuma
    Masuda, Hiroshi
    [J]. INTERNATIONAL JOURNAL OF AUTOMATION TECHNOLOGY, 2021, 15 (03) : 258 - 267
  • [5] Human Activity Recognition From Accelerometer Data Using Convolutional Neural Network
    Lee, Song-Mi
    Yoon, Sang Min
    Cho, Heeryon
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP), 2017, : 131 - 134
  • [6] Status detection from spatial-temporal data in pipeline network using data transformation convolutional neural network
    Hu, Xuguang
    Zhang, Huaguang
    Ma, Dazhong
    Wang, Rui
    [J]. NEUROCOMPUTING, 2019, 358 : 401 - 413
  • [7] Classification of Eye Tracking Data using a Convolutional Neural Network
    Yin, Yuehan
    Juan, Chunghao
    Chakraborty, Joyram
    McGuire, Michael P.
    [J]. 2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2018, : 530 - 535
  • [8] Using convolutional neural network autoencoders to understand unlabeled data
    Edwards, Samuel
    Lee, Michael S.
    [J]. ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS, 2019, 11006
  • [9] Data Augmentation Using Contour Image for Convolutional Neural Network
    Hwang, Seung-Yeon
    Kim, Jeong-Joon
    [J]. CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 75 (03): : 4669 - 4680
  • [10] Assessment of the Clusterability of Data Using a Multimodal Convolutional Neural Network
    Reunanen, Niko
    Raty, Tomi
    Lintonen, Timo
    Jokinen, Juho J.
    [J]. IEEE Transactions on Artificial Intelligence, 2022, 3 (03): : 355 - 369