• About
  • Policies
  • What is open access
  • Library
  • Contact
Advanced search
      View Item 
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Department of Computer Engineering
      • Dept. of Computer Engineering - Master's degree
      • View Item
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Department of Computer Engineering
      • Dept. of Computer Engineering - Master's degree
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Learning efficient visual embedding models under data constraints

      Thumbnail
      View / Download
      7.9 Mb
      Author(s)
      Sarıyıldız, Mert Bülent
      Advisor
      Aksoy, Selim
      Date
      2019-09
      Publisher
      Bilkent University
      Language
      English
      Type
      Thesis
      Item Usage Stats
      287
      views
      318
      downloads
      Abstract
      Deep learning models require large-scale datasets to learn rich sets of low and mid-level patterns and high-level semantics. Therefore, given a high-capacity neural network, one way to improve the performance of a model is increasing the size of the dataset which the model is trained over on. Considering that it is easy to get the amount of computational power required to train a network, data becomes a serious bottleneck in scaling up the existing machine learning pipelines. In this thesis, we look into two main data bottlenecks that rise in computer vision applications: I. the difficulty of finding training data for diverse sets of object categories, II. the complication of utilizing data containing sensitive user information for the purpose of training neural network models. To address these issues, we study zero-shot learning and decentralized learning schemes, respectively. Zero-shot learning (ZSL) is one of the most promising problems where substantial progress can potentially be achieved through unsupervised learning, due to distributional differences between supervised and zero-shot classes. For this reason, several works investigate the incorporation of discriminative domain adaptation techniques into ZSL, which, however, lead to modest improvements in ZSL accuracy. In contrast, we propose a generative model that can naturally learn from unsupervised examples, and synthesize training examples for unseen classes purely based on their class embeddings, and therefore, reduce the zero-shot learning problem into a supervised classification task. The proposed approach consists of two important components: I. a conditional Generative Adversarial Network that learns to produce samples that mimic the characteristics of unsupervised data examples, and II. the Gradient Matching (GM) loss that measures the quality of the gradient signal obtained from the synthesized examples. Using our GM loss formulation, we enforce the generator to produce examples from which accurate classifiers can be trained. Experimental results on several ZSL benchmark datasets show that our approach leads to significant improvements over the state of the art in generalized zero-shot classification. Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by their owners. However, recently, it has been shown that the existing collaborative learning frameworks are vulnerable to an active adversary that runs a generative adversarial network (GAN) attack. In this work, we propose a novel classification model that is resilient against such attacks by design. More specifically, we introduce a key-based classification model and a principled training scheme that protects class scores by using class-specific private keys, which effectively hides the information necessary for a GAN attack. We additionally show how to utilize high dimensional keys to improve the robustness against attacks without increasing the model complexity. Our detailed experiments demonstrate the effectiveness of the proposed technique.
      Keywords
      Zero-shot learning
      Meta learning
      Generative models
      Privacypreserving machine learning
      Collaborative learning
      Cassification, generative adversarial networks
      Permalink
      http://hdl.handle.net/11693/52409
      Collections
      • Dept. of Computer Engineering - Master's degree 566
      Show full item record

      Related items

      Showing items related by title, author, creator and subject.

      • Thumbnail

        Adaptive ensemble learning with confidence bounds for personalized diagnosis 

        Tekin, Cem; Yoon, J.; Van Der Schaar, M. (AAAI Press, 2016)
        With the advances in the field of medical informatics, automated clinical decision support systems are becoming the de facto standard in personalized diagnosis. In order to establish high accuracy and confidence in ...
      • Thumbnail

        The effect of uncertainty on learning in game-like environments 

        Ozcelik, E.; Cagiltay, N. E.; Ozcelik, N. S. (Pergamon Press, 2013)
        Considering the role of games for educational purposes, there has an increase in interest among educators in applying strategies used in popular games to create more engaging learning environments. Learning is more fun and ...
      • Thumbnail

        Big-data streaming applications scheduling based on staged multi-armed bandits 

        Kanoun, K.; Tekin, C.; Atienza, D.; Van Der Schaar, M. (Institute of Electrical and Electronics Engineers, 2016)
        Several techniques have been recently proposed to adapt Big-Data streaming applications to existing many core platforms. Among these techniques, online reinforcement learning methods have been proposed that learn how to ...

      Browse

      All of BUIRCommunities & CollectionsTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCoursesThis CollectionTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCourses

      My Account

      Login

      Statistics

      View Usage StatisticsView Google Analytics Statistics

      Bilkent University

      If you have trouble accessing this page and need to request an alternate format, contact the site administrator. Phone: (312) 290 2976
      © Bilkent University - Library IT

      Contact Us | Send Feedback | Off-Campus Access | Admin | Privacy