Skip to main content ITU
Logo
  • Programmes
    • BSc Programmes
    • BSc in Global Business Informatics
    • BSc in Digital Design and Interactive Technologies
    • BSc in Software Development
    • BSc in Data Science
    • Applying for a BSc Programme
    • MSc Programmes
    • MSc in Digital Innovation & Management
    • MSc in Digital Design and Interactive Technologies
    • MSc in Software Design
    • MSc in Computer Science
    • MSc in Data Science
    • MSc in Games
    • Applying for an MSc Programme
    • Student Life
    • Women in tech
    • Student Organisations at ITU
    • Labs for students
    • Practical Information for International Students
    • Study Start
    • Study and Career Guidance
    • Guest Students
    • Who can be a Guest Student
    • ITU Summer University
    • Exchange Student
    • Become an exchange student at ITU
    • Open House
    • Open House - MSc Programmes
    • Open House - BSc programmes
  • Professional Education
    • Master in IT
    • Master in IT Management
    • Single Subjects
    • About single subjects
    • Contact
    • Contact us here
  • Research
    • Departments
    • Business IT Department
    • Computer Science Department
    • Digital Design Department
    • Research Groups and Labs
    • Research Groups
    • Labs
    • Research Centres
    • Centre for Computer Games Research
    • Center for Computing Education Research
    • Centre for Digital Welfare
    • Centre for Information Security and Trust
    • European Blockchain Centre
    • Research Centre for Government IT
    • Research Institutes
    • Danish Institute for IT Program Management
    • Selected Research Themes
    • Artificial intelligence
    • Big Data
    • Climate IT
    • Computer games
    • Blockchain
    • Digitalization
    • IT security
    • Find a Researcher
    • Faculty Search
    • PhD Programme
    • About the PhD Programme
    • Available PhD Positions
    • PhD Courses
    • Research Ethics and Integrity
    • Good Scientific Practice
    • PhD Defences
    • Technical Reports
    • Technical Reports
  • Collaboration
    • Collaboration with students
    • Project collaboration
    • Project Market
    • Student worker
    • Project postings
    • Job and Project bank
    • Portraits of ITU graduates
    • Employer Branding
    • IT Match Making
    • Hiring an ITU student or graduate
    • Make a post in the job bank
    • Research collaboration
    • Licensing Opportunities
    • Open Entrepreneurship
    • Research collaboration
    • Industrial PhD
    • Hire an Industrial PhD
    • Innovation and entrepreneurship
    • ITU Business Development
    • ITU Startup programme
    • Startup stories
  • About ITU
    • Vacancies
    • Press
    • ITU Alumni
    • News
    • Calendar
    • Contact
    • About ITU
  • DK
PhD Courses
ITU  /  Research  /  PhD Programme  /  PhD Courses  /  PhD courses 2022  /  PhD Study Group - Deep Generative Models
  • Research
    • Research Departments
    • Research Ethics and Integrity
    • Good Scientific Practice
    • Research Groups and Centers
    • Labs
    • Technical Reports
    • PhD Programme
      • Industrial PhD
      • Marie Curie European Industrial PhD
      • Project PhD
      • Institute PhD
      • Independent PhD - Tuition Fee Free
      • PhD Positions
      • PhD Courses
        • PhD courses 2022
          • PhD Course - International Blockchain School - Winter Edition
          • Literature management module 1 - Academic information seeking and reference management
          • Literature management module 2 - Literature reviews: planning and searching for evidence
          • Literature management module 3 Researcher’s rights to scientific works and Anti-plagiarism screening
          • PhD Course - An Introduction to Data Visualization and Data Visualization Technology
          • PhD Course - Critical Participatory Research and Design
          • PhD Course - Deep Learning - A Computational Efficiency Perspective
          • PhD Course - Eludamos Symposium Doctoral Consortium
          • PhD Course - Experimenting with ethnography
          • PhD Course - Polynomials and algebraic complexity theory
          • PhD Course - Program Verification
          • PhD Course - Research Code of Conduct
          • PhD Reading Group - Introductory Formal Methods
          • PhD Study Group - Deep Generative Models
            • PhD Symposium - Into the academic Werkstatt - the craft of writing and preparing for publication
          • PhD courses 2021
          • PhD courses 2020
          • PhD Courses 2019
          • PhD Courses 2018
          • PhD courses 2017
          • PhD courses 2016
          • PhD courses 2015
          • PhD courses 2014
          • PhD courses 2013
          • PhD courses 2012
          • PhD courses 2011
          • PhD courses 2010
        • PhD Defences
        • PhD Handbook
        • PhD Support
      • Center for Digital Welfare

    PhD Study Group - Deep Generative Models

    Organizer(s):

    • Imke Grabe, Miguel González Duque (PhD Students at Digital Design)
    • René Haas (PhD student at Computer Science)
    • Sami Brandt (Associate Professor at Computer Science)    

    Lecturers:

    • Each participant is responsible for presenting one reading and leading the discussion. 

    Date(s) of the course: 14.01.2022, 21.01.2022, 04.02.2022

    Time: 10.00-12.00

    Room: 2A05

    Course description:

    In this study group, we plan to study the state-of-the-art of Deep Generative Modelling. More specifically, we will discuss 6 different papers (see Reading List below). Focus will be set on the technical aspects of underlying the models, comparing different generative models, and discussing their application in the participants’ respective PhD projects. The course will focus on probabilistic generative models such as variational autoencoders, implicit generative models, such as generative adversarial networks as well as autoregressive models.

    We will meet in three sessions. For each session, participants prepare two readings. A reading is presented by one participant and discussed in the group. After the presentation the student will receive feedback on the presentation from the other participants. Readings are allocated in the week of the course start.

    Intended learning outcomes: 

    • Having completed the successfully, PhD students will:
    • Be able to analyze, discuss and reflect on recent publications in the field in generative modeling. 
    • Be able to compare different generative models and reflect on their application. 
    • Be able to confidently communicate recent research in the field of generative modelling to peers. 

    Reading List

    Reading list:

    [1] Gulrajani, Ishaan, Kundan Kumar, Faruk Ahmed, Adrien Ali Taiga, Francesco Visin, David Vazquez, and Aaron Courville. “PixelVAE: A Latent Variable Model for Natural Images,” no. 701 (2017): 447–54.

    [2] Hoogeboom, Emiel, Didrik Nielsen, Priyank Jaini, Patrick Forré, and Max Welling. “Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions.” ArXiv:2102.05379 [Cs, Stat], October 22, 2021. http://arxiv.org/abs/2102.05379. (Accepted at NeurIPS 2021)

    [3] Esser, Patrick, Robin Rombach, and Björn Ommer. 2021. “Taming Transformers for High-Resolution Image Synthesis.” ArXiv:2012.09841 [Cs], June. http://arxiv.org/abs/2012.09841.

    [4] Karras, Tero, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. “Analyzing and Improving the Image Quality of StyleGAN.” ArXiv:1912.04958 [Cs, Eess, Stat], March. http://arxiv.org/abs/1912.04958.

    [5] Bau, David, Steven Liu, Tongzhou Wang, Jun-Yan Zhu, and Antonio Torralba. “Rewriting a Deep Generative Model.” ArXiv:2007.15646 [Cs], July 30, 2020. http://arxiv.org/abs/2007.15646.

    [6] Sauer, Axel, and Andreas Geiger. “Counterfactual Generative Networks.” ArXiv:2101.06046 [Cs], January 15, 2021. http://arxiv.org/abs/2101.06046.

    Programme

    Programme:

    14.01.2022: Readings [1] and [2] are presented and discussed.

    21.01.2022: Readings [3] and [4] are presented and discussed.

    04.02.2022: Readings [5] and [6] are presented and discussed.

    More specifically, a session will follow the following plan:

    Time

    Program point

    10.00-10.25

    Paper presentation 1

    10.25-10.55

    Discussion of paper 1, based on the prepared discussion points and questions

    10.55-11.00

    Small break

    11.00-11.25

    Paper presentation 2

    11.25-11.55

    Discussion of paper 2, based on the prepared discussion points and questions

    11.55-12.00

    Wrap up of today’s papers

    Prerequisites:

    Participants are expected to know the basics of at least one deep generative model (e.g. how a Generative Adversarial Network or a Variational AutoEncoder works).

    Exam:

    Participants will be examined based on the presentations given during the course.

    Credits:

    Participants receive 1.5 ECTS upon participation in all meetings and the presentation of one paper.

    Amount of hours the student is expected to use on the activity:

    • Participation: 6 in person
    • Preparation: 35 hours reading papers and preparing slides

    How to sign up: Contact Imke Grabe at imgr@itu.dk by Tuesday, 12.01.2022

    Contact us

    Phone
    +45 7218 5000
    E-mail
    itu@itu.dk

    All contact information

    Web Accessibility Statement

    Find us

    IT University of Copenhagen
    Rued Langgaards Vej 7
    DK-2300 Copenhagen S
    Denmark
    How to get here

    Follow us

    ITU Student /
    Privacy /
    EAN-nr. 5798000417878/
    CVR-nr. 29 05 77 53

    This page is printed from https://en.itu.dk/research/portalplaceholder?layoutfraction=top&langRef=https://pure.itu.dk/portal/da/organisations/digital-design(d065e6c2-4fae-4d68-ad04-70aec25d2d5e)/clippings.html?page=29