Scarcity and imbalance of the training data usually hinder adversarial networks to have proper training and thus make it difficult for the framework to learn representations with adequate quality. This is especially true when rare instances look kind of exotic compared to the rest of the instances in the dataset. In this work, we investigate approaches for leveraging relevant knowledge from a different dataset to improve the model performance and demonstrate that auxiliary data enables the networks to learn underrepresented features.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen


    Exportieren, teilen und zitieren



    Titel :

    A Search for Visual Features in Adversarial Networks


    Beteiligte:
    Dehghani, Farzaneh (Autor:in) / Ghorban, Farzin (Autor:in) / Velten, Joerg (Autor:in) / Kummert, Anton (Autor:in)

    Kongress:

    AmE 2020 – Automotive meets Electronics - 11. GMM-Fachtagung ; 2020 ; Dortmund, Deutschland


    Erscheinungsdatum :

    01.01.2020


    Format / Umfang :

    6 pages


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Investigating the Generation of Adversarial Malware Features and the Use of Adversarial Training

    Djaneye-Boundjou, Ouboti / Messay-Kebede, Temesguen / Kapp, David | IEEE | 2021



    Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA

    Mori, G. / Malik, J. / IEEE | British Library Conference Proceedings | 2003


    Accumulation of adversarial examples for underwater visual object tracking

    Zhang, Yu / Li, Jin / Zhang, Chenghao | British Library Conference Proceedings | 2022