Dual Deep Neural Network Approach to Matching Data in Different Modes

Mark Eastwood, Chrisina Jayne

    Research output: Chapter in Book/Report/Conference proceedingChapter

    5 Citations (Scopus)

    Abstract

    This paper investigates the application of a novel Deep Neural Network (DNN) architecture to the problem of matching data in different modes. Initially one DNN is pre-trained as a feature extractor using several stacked Restricted Boltzmann Machine (RBM) blocks on the entire training data using unsupervised learning. This DNN is duplicated and each net is fine-tuned by training on the data represented in a specific mode using supervised learning. The target of each DNN is linked to the output from the other DNN thus ensuring matching features are learnt which are adjusted to take differing representation into account. These features are used with some distance metric to determine matches. The expected benefit of this approach is utilizing the capability of DNN to learn higher level features which can better capture the information contained in the input data's structure, while ensuring the differences in data representation are accounted for. The architecture is applied to the problem of matching faces and sketches and the results compared to traditional approaches employing Principal Component Analysis (PCA) or Linear Discriminant Analysis (LDA).
    Original languageEnglish
    Title of host publicationInternational Joint Conference on Neural Networks, IJCNN 2014
    PublisherIEEE
    Pages1688-1694
    VolumeArticle number 6889877
    ISBN (Print)978-147991484-5
    DOIs
    Publication statusPublished - 3 Sep 2014
    EventNeural Networks, 2014 International Joint Conference - Beijing, China
    Duration: 6 Jul 201411 Jul 2014

    Conference

    ConferenceNeural Networks, 2014 International Joint Conference
    Abbreviated titleIJCNN
    CountryChina
    CityBeijing
    Period6/07/1411/07/14

    Bibliographical note

    This conference paper is not yet available on the repository. The paper was given at the International Joint Conference on Neural Networks, IJCNN 2014; Beijing; China; 6 July 2014 through 11 July 2014

    Fingerprint Dive into the research topics of 'Dual Deep Neural Network Approach to Matching Data in Different Modes'. Together they form a unique fingerprint.

  • Cite this

    Eastwood, M., & Jayne, C. (2014). Dual Deep Neural Network Approach to Matching Data in Different Modes. In International Joint Conference on Neural Networks, IJCNN 2014 (Vol. Article number 6889877, pp. 1688-1694). IEEE. https://doi.org/10.1109/IJCNN.2014.6889877