Hauptseminar/Master Seminar:
Deep Generative Models SS2018

Team: Prof. Nassir Navab, Dr. Vasileios Belagiannis, Dr. Federico Tombari, Iro Laina, Magda Paschali, Leslie Casas, Oliver Scheel

Type: Advanced Seminar Course Module IN0014
Type: Master Seminar Module IN2107
Type: Seminar Module IN4826
SWS: 2+0
ECTS: 5 Credits
Location: MI 03.13.010
Time: 16:00 - 18:00
Course Language: English

Announcements

• 03.02.2018 - Motivation letters are welcomed.
• 21.01.2018 - Preliminary meeting 25.01.2018 at 11:00 - 12:00 at MI 03.13.010.
• 14.01.2018 - The seminar Deep Generative Models will be offered for the Summer Semester 2018. The web-site will be updated soon.

Introduction

• The recent advances of generative models in Deep Learning will be studied in the Seminar Course. Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), adversarial learning and learning with adversaries compose the main topics of the seminar. A set of papers will cover the aforementioned topics. One or two lectures will be also offered to support the seminar.

Registration

• Preliminary Meeting: 25.01.2018 at 11:00 - 12:00 at MI 03.13.010.
• The registration is though the TUM Matching Platform.

Requirements

In this Seminar (formerly Hauptseminar), each student is asked to select one paper from a list. In order to successfully complete the seminar, participants have to fulfill these requirements:

• Presentation: The selected paper is presented to the other participants (20 minutes presentation 10 minutes questions). Use the CAMP templates for PowerPoint camp-tum-jhu-slides.zip, or Latex: CAMP-latex-template.
• Written Report: A document of maximum 8 pages is written and submitted one week after the presentation. Please download and use the llncs2e.zip Latex template.
• Attendance: Participants have to participate actively in all seminar sessions.

The students are required to attend each seminar presentation which will be held during this course. Each presentation is followed by a discussion and everyone is encouraged to actively participate. Part of the discussions outcome will be included in the report too. The report must include all references used and must be written completely in your own words. Copy and paste will not be tolerated. Both report and presentation have to be done in English.

List of Publications

Nr	Authors	Title	Conference	Link	Tutor	Student
01	Arjovsky, Martin and Bottou Leon	Towards principled methods for training generative adversarial networks	ICLR 2017	https://arxiv.org/pdf/1701.04862.pdf	Vasilis	Fabian H.
02	Ilya Tolstikhin, Olivier Bousquet, Sylvain Gelly, Bernhard Schoelkopf	Wasserstein Auto-Encoders	ICLR 2018	https://arxiv.org/abs/1711.01558	Kristians	Nathanael B.
03	Justin Johnson, Alexandre Alahi, Li Fei-Fei	Perceptual Losses for Real-Time Style Transfer and Super-Resolution	ECCV 2016	https://arxiv.org/abs/1603.08155	Oliver	Sangram G.
04	Ashish Bora, Eric Price, Alexandros G. Dimakis	AmbientGAN?: Generative models from lossy measurements	ICLR 2018	https://openreview.net/forum?id=Hy7fDog0b	Helisa	Deepita P.
05	Achlioptas, Panos and Diamanti, Olga and Mitliagkas, Ioannis and Guibas, Leonidas	Learning Representations and Generative Models for 3D Point Clouds	arxiv 2017	https://arxiv.org/abs/1707.02392	Federico	Thi Kim T. T.
06	Anh Nguyen, Jeff Clune, Yoshua Bengio, Alexey Dosovitskiy, Jason Yosinski	Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space	CVPR 2017	https://arxiv.org/abs/1612.00005	Kristians	Pooja K.
07	Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T. Freeman, Joshua B. Tenenbaum	Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling	NIPS 2016	https://arxiv.org/abs/1610.07584	Federico	Henrique R.
08	Yunchen Pu, Weiyao Wang, Ricardo Henao, Liqun Chen, Zhe Gan, Chunyuan Li, Lawrence Carin	Adversarial Symmetric Variational Autoencoder	NIPS 2017	https://arxiv.org/abs/1711.04915	Leslie	Karl S.
09	Qi Wu, Peng Wang, Chunhua Shen, Ian Reid, Anton van den Hengel	Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning	CVPR 2018	https://arxiv.org/abs/1711.07613	Iro	Farrukh M.
10	William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed, Ian Goodfellow	Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step	ICLR 2018	https://openreview.net/forum?id=ByQpn1ZA-	Oliver	Juliane A.
11	Gamaleldin F. Elsayed, Shreya Shankar, Brian Cheung, Nicolas Papernot, Alex Kurakin, Ian Goodfellow, Jascha Sohl-Dickstein	Adversarial Examples that Fool both Human and Computer Vision	Arxiv 2018	https://arxiv.org/abs/1802.08195	Magda	Jonas H.
12	Nir Baram, Oron Anschel, Itai Caspi, Shie Mannor	End-to-End Differentiable Adversarial Imitation Learning	ICML 2017	http://proceedings.mlr.press/v70/baram17a/baram17a.pdf	Vasilis	Harris J.
13	Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb	Learning from Simulated and Unsupervised Images through Adversarial Training	CVPR 2017	https://arxiv.org/abs/1612.07828	Leslie	Shyam A.
14	Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, Aaron Courville	Improved Training of Wasserstein GANs.	NIPS 2017	https://arxiv.org/pdf/1704.00028.pdf	Magda	Yelysei B.

Schedule

The schedule for the paper presentations will be announced here during the semester. Each student is required to attend all presentations.

Date	Time	Title	Speaker	Material
18.04.2018	16:00 - 18:00	Lecture	Vasileios Belagiannis	Slides, Code
25.04.2018	16:00 - 18:00	3 Presentations (tbd)	Fabian H., Nathanael B., Sangram G.
02.05.2018	16:00 - 18:00	3 Presentations (tbd)	Deepita P., Thi Kim T. T., Pooja K.
09.05.2018	16:00 - 18:00	3 Presentations (tbd)	Henrique R., Karl S., Farrukh M.
23.05.2018	16:00 - 18:00	3 Presentations (tbd)	Juliane A., Jonas H.
06.06.2018	16:00 - 18:00	2 Presentations (tbd)	Shyam A., Yelysei B., Harris J.