This paper presents a mathematical framework for visual learning that integrates two popular statistical learning paradigms in the literature: (I). Descriptive learning, such as Markov random fields and minimax entropy learning, and (II). Generative learning, such as PCA, ICA, TCA, image coding and HMM. We apply this integrated learning framework to texton modeling, and we assume that an observed texture image is generated by multiple layers of hidden stochastic "texton processes" with each texton being a window function, like a mini-template or a wavelet, under affine transformations. The spatial arrangements of the textons are characterized by minimax entropy models. The texton processes generate images by occlusion or linear addition. Thus given a raw input image, the learning framework achieves four goals: (i). Computing the appearance of the textons. (ii) Inferring the hidden stochastic texton processes. (iii). Learning Gibbs models for each texton process and (iv). Verifying the learnt textons and Gibbs models through random sampling and texture synthesis. The integrated framework subsumes the minimax entropy learning paradigm and creates a richer class of probability models for visual patterns, which are suited for middle level vision representations. Furthermore we show that the integration of description and generative methods yields a natural and general framework of visual learning. We demonstrate the proposed framework and algorithms on many real images.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Visual learning by integrating descriptive and generative methods


    Beteiligte:
    Gheng-En Guo, (Autor:in) / Song-Chun Zhu, (Autor:in) / Yingnian Wu, (Autor:in)


    Erscheinungsdatum :

    01.01.2001


    Format / Umfang :

    1183037 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Visual Learning by Integrating Descriptive and Generative Methods

    Guo, C. / Zhu, S. / Wu, Y. et al. | British Library Conference Proceedings | 2001


    Modeling Visual Patterns by Integrating Descriptive and Generative Methods

    Guo, C. E. / Zhu, S. C. / Wu, Y. N. | British Library Online Contents | 2003


    HKGAIL: Policy shaping via integrating human knowledge with generative adversarial imitation learning

    Peng, Yanfei / Tan, Guozhen / Si, Huaiwei | Wiley | 2023

    Freier Zugriff


    Hybrid Generative-Discriminative Visual Categorization

    Holub, A. D. / Welling, M. / Perona, P. | British Library Online Contents | 2008