Course Information

Course Title: Deep Learning for Computer Vision: Seminal Work

Course ID: 263-5904-00S

Lecturers: Dr. Hermann Blum

Teaching Assistants: Zador Pataki, Tobias Fischer, Philipp Lindenberger, Paper Supervisors

Venue: Mo 16-18h, CAB G 57

Course Description :

This seminar covers seminal papers on the topic of deep learning for computer vision. The students will present and discuss the papers and gain an understanding of the most influential research in this area - both past and present. The objectives of this seminar are two-fold. Firstly, the aim is to provide a solid understanding of key contributions to the field of deep learning for vision (including a historical perspective as well as recent work). Secondly, the students will learn to critically read and analyse original research papers and judge their impact, as well as how to give a scientific presentation and lead a discussion on their topic.

Each student chooses one paper from the provided collection to present during the course of the seminar. The students will be supported in the preparation of their presentation by the seminar assistants.

Important Information

Recommended Textbooks for Reference
Image Processing
  • Class Material:
  • Class material will be posted on Moodle. We will also use Moodle to submit assignments.
  • Assignments:
  • Each student will present one paper. Everybody is encouraged to read each paper before it is being presented and engage in a discussion following the presentations. To foster interesting discussions, each paper will also be assigned to a "critic" who studies the paper and shortly presents a summary of the paper's weaknesses.
  • Grading:
  • Each student will be graded based on their presentation (70%) and their participation in the assigned discussions (20%). There is a small participation grade (10%) for those that ask questions in papers even if they are not assigned to them.
  • Attendance:
  • Attendance is required to pass the course (3 absences allowed).
  • The class is held in person, except if otherwise stated.


Date Topic Presenter Critics Assistant
19.02 Introduction
26.02 #01. ImageNet Classification with Deep Convolutional Neural Networks Christopher Kotthoff Felix Möller Petr Hruby
26.02 #02. Dropout: A simple way to prevent neural networks from overfitting - - Philipp Lindenberger
04.03 #03. Understanding Batch Normalization Wenqing Wang Denis Sutter Denys Rozumnyi
04.03 #04. Deep residual learning for image recognition Kevin Rohner Yves Stebler Denys Rozumnyi
11.03 #05. Attention Is All You Need Théo Ducrey Endi Kucuku Linfei Pan
11.03 #06. Emerging Properties in Self-Supervised Vision Transformers (DINO) Vansh Gupta Bastian Schildknecht Boyang Sun
18.03 #07. U-Net: Convolutional Networks for Biomedical Image Segmentation Andreas Psaroudakis Théo Ducrey Yung-Hsu (Roy) Yang
18.03 #08. You only look once: Unified, real-time object detection Felix Möller Ming-Han Lee Tobias Fischer
18.03 #09. Segment Anything Onat Vuran Orhun Görkem Jonas Hein
25.03 #10. What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? David Schnurr Kevin Rohner Zador Pataki
25.03 #11. On Calibration of Modern Neural Networks Endi Kucuku Vansh Gupta Jonas Hein
08.04 #12. RAFT: Recurrent All-Pairs Field Transforms for Optical Flow Hei Yi Mak Wenqing Wang Haofei Xu
22.04 #14. ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases Orhun Görkem Andreas Psaroudakis Hermann Blum
22.04 #15. High-resolution image synthesis with latent diffusion models Bastian Schildknecht Christopher Kotthoff Fangjinhua Wang
29.04 #16. Denoising Diffusion Probabilistic Models Philipp Brodmann Onat Vuran Zuoyue Li
29.04 #17. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks Ming-Han Lee Jannek Ulm Botao Ye
06.05 #18. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis Kacper Ozieblowski Philipp Brodmann Tobias Fischer
06.05 #19. Convolutional Occupancy Networks Sayan Deb Sarkar David Schnurr Songyou Peng
13.05 #20. SuperPoint: Self-Supervised Interest Point Detection and Description Hardik Shah Sayan Deb Sarkar Zador Pataki
13.05 #21. Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC Yves Stebler Zhao Huang Daniel Barath
27.05 #22. Learning Transferable Visual Models From Natural Language Supervision Denis Sutter Hei Yi Mak Francis Engelmann
27.05 #23. Scaling Open-Vocabulary Image Segmentation with Image-Level Labels Zhao Huang Hardik Shah Jiaqi Chen
27.05 #13. Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation Jannek Ulm Kacper Ozieblowski Hermann Blum