CS 717: Seminar on Computer Vision

The Computer Vision seminar covers recent topics in computer vision. In FSS2021, the seminar will be on „Neural Architectures for Vision“ with focus on alternatives to pure CNNs.

Organization

  • This seminar is organized by Prof. Dr.-Ing. Margret Keuper
  • Available for Master students (2 SWS, 4 ECTS)
  • Prerequisites: solid background in machine learning
  • Maximum number of participants is 10 students

Goals

In this seminar, you will

  • Read, understand, and explore scientific literature
  • Summarize a current research topic in a concise report (10 single-column pages + references)
  • Give two presentations about your topic (3 minutes flash presentation, 15 minutes final presentation)
  • Moderate a scientific discussion about the topic of one of your fellow students
  • Review a (draft of a) report of a fellow student

Schedule

  • Register as described below.
  • Attend the kickoff meeting on 11 March, 5.15 pm. The kickoff meeting will be held via zoom – see Portal2 for the link.
  • Work individually throughout the semester according to the seminar schedule.
  • Meet your advisor for guidance and feedback.

Flash Presentations

April 22nd (preliminary)

Topics: TBA

 

Final Presentations

Final presentations will take place via zoom. Preliminary dates: June 9th, 5pm

Registration

Register via Portal 2.

If you are accepted into the seminar, provide at least 3 topics of your preference (your own and/or example topics; see below) by 11 March via email to Margret Keuper. The actual topic assignment takes place soon afterwards; we will notify you via email. Our goal is to assign one of your preferred topics to you.

Topics

Each student works on a topic within the area of the seminar along with an accompanying reference paper. Your presentation and report should explore the topic with an emphasis on the reference paper, but not just the reference paper.

We strongly encourage you to explore the available literature and suggest a topic and reference paper of your own choice. Reference papers should be strong papers from a major venue; contact us if you are unsure.

We provide example topics and reference papers below .

 

Topic List:

[1] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Dosovitskiy et al., ICLR 2021

[2] CrossTransformers: spatially-aware few-shot transfer. Doersch et al., NeurIPS 2020

[3] Image Classification with Hierarchical Multigraph Networks, Knyazev et al. BMVC 2019

[4] DeepCaps: Going Deeper with Capsule Networks, Rajasegaran et al., CVPR 2019

[5] Transforming auto-encoders, Hinton et al., International Conference on Artificial Neural Networks, 2011

[6] Deep convolutional inverse graphics network, Kulkarni et al., Advances in neural information processing systems. 2015

[7] Dynamic Filter Networks, De Brabandere et al., NIPS 2016

[8] Non-linear Convolution Filters for CNN-based Learning, Zoumpourlis et al., ICCV 2017

 

 

References

Writing for Computer Science by Justin Zobel, Springer, 2014