A Joint Discriminative Generative Model for Deformable Model Construction and Classification

Ioannis Marras, Symeon Nikitidis, Stefanos Zafeiriou, Maja Pantic

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    Discriminative classification models have been successfully applied for various computer vision tasks such as object and face detection and recognition. However, deformations can change objects coordinate space and perturb robust similarity measurement, which is the essence of all classification algorithms. The common approach to deal with deformations is either to seek for deformation invariant features or to develop models that describe objects deformations. However, the former approach requires a huge amount of data and a good amount of engineering to be properly trained, while the latter require considerable human effort in the form of carefully annotated data. In this paper, we propose a method that jointly learns with minimal human intervention a generative deformable model using only a simple shape model of the object and images automatically downloaded from the Internet, and also extracts features appropriate for classification. The proposed algorithm is applied on various classification problems such as 'in-thewild' face recognition, gender classification and eye glasses detection on data retrieved by querying into a web image search engine. We demonstrate that not only it outperforms other automatic methods by large margins, but also performs comparably with supervised methods trained on thousands of manually annotated data.

    Original languageEnglish
    Title of host publication12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017)
    PublisherIEEE
    Pages127-134
    Number of pages8
    ISBN (Electronic)9781509040230
    ISBN (Print)978-1-5090-4024-7
    DOIs
    Publication statusPublished - 28 Jun 2017
    Event12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - Washington, United States
    Duration: 30 May 20173 Jun 2017
    Conference number: 12
    http://www.fg2017.org/

    Conference

    Conference12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017
    Abbreviated titleFG
    CountryUnited States
    CityWashington
    Period30/05/173/06/17
    Internet address

      Fingerprint

    Cite this

    Marras, I., Nikitidis, S., Zafeiriou, S., & Pantic, M. (2017). A Joint Discriminative Generative Model for Deformable Model Construction and Classification. In 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) (pp. 127-134). [7961732] IEEE. https://doi.org/10.1109/FG.2017.24