• Login
    View Item 
    •   Home
    • Research
    • Conference Papers
    • View Item
    •   Home
    • Research
    • Conference Papers
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguideTheses and Dissertations LibguideSubmit an Item

    Statistics

    Display statistics

    GDPP: Learning Diverse Generations using Determinantal Point Processes

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    elfeki19a.pdf
    Size:
    1.113Mb
    Format:
    PDF
    Description:
    Conference Paper
    Download
    Thumbnail
    Name:
    elfeki19a-supp.pdf
    Size:
    1.469Mb
    Format:
    PDF
    Description:
    Supplemental Material
    Download
    Type
    Conference Paper
    Authors
    Elfeki, Mohamed
    Couprie, Camille
    Rivière, Morgane
    Elhoseiny, Mohamed cc
    KAUST Department
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Date
    2019-01-01
    Submitted Date
    2018-11-30
    Permanent link to this record
    http://hdl.handle.net/10754/662645
    
    Metadata
    Show full item record
    Abstract
    Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic looking images. An essential characteristic of generative models is their ability to produce multimodal outputs. However, while training, they are often susceptible to mode collapse, that is models are limited in mapping input noise to only a few modes of the true data distribution. In this work, we draw inspiration from Determinantal Point Process (DPP) to propose an unsupervised penalty loss that alleviates mode collapse while producing higher quality samples. DPP is an elegant probabilistic measure used to model negative correlations within a subset and hence quantify its diversity. We use DPP kernel to model the diversity in real data as well as in synthetic data. Then, we devise an objective term that encourages generator to synthesize data with a similar diversity to real data. In contrast to previous state-of-the-art generative models that tend to use additional trainable parameters or complex training paradigms, our method docs not change the original training scheme. Embedded in an adversarial training and variational autoencoder, our Generative DPP approach shows a consistent resistance to mode-collapse on a wide-variety of synthetic data and natural image datasets including MNIST, CIFAR10, and CelcbA, while outperforming state-of-the-art methods for data-efficiency, generation quality, and convergence-time whereas being 5.8x faster than its closest competitor.
    Citation
    International Conference on Machine Learning 2019
    Publisher
    International Machine Learning Society (IMLS)rasmussen@ptd.net
    Conference/Event name
    36th International Conference on Machine Learning, ICML 2019
    ISBN
    9781510886988
    arXiv
    1812.00068
    Additional Links
    http://proceedings.mlr.press/v97/elfeki19a.html
    Relations
    Is Supplemented By:
    • [Software]
      Title: M-Elfeki/GDPP: Generator loss to reduce mode-collapse and to improve the generated samples quality.. Publication Date: 2018-11-30. github: M-Elfeki/GDPP Handle: 10754/667580
    Collections
    Conference Papers; Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2023  DuraSpace
    Quick Guide | Contact Us | KAUST University Library
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.