ETH Zurich - D-INFK - IVC - CVG - Lectures - Deep Learning Seminar

Deep Learning Seminar

Course title: Deep Learning for Computer Vision: Seminal Work
Course ID: 263-5904-00L
Lecturers: Dr. Hermann Blum, Dr. Iro Armeni
Teaching Assistants Rémi Pautrat, Paper supervisors
Venue: Mo 16-18h, CAB G 57

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

  • 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 two "critics" who study the paper and prepare questions for the discussion.
  • Grading: Each student will be graded based on both their presentation (75%) and their participation in the assigned discussions (20%). There is a small participation grade (5%) 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
20.02. Introduction
27.02. #01. ImageNet Classification with Deep Convolutional Neural Networks Sofie Daniels Felix Yang, Zhaochong An Petr Hrubý
27.02. #02. Visualizing and Understanding Convolutional Networks Benedikt Schesch Julian Sainz Martinez, Oliver Lemke Philipp Lindenberger
06.03. #03. U-Net: Convolutional Networks for Biomedical Image Segmentation Julian Sainz Martinez Mathias Vogel Hüni, Yuqing Huang Linfei Pan
06.03. #04. Deep residual learning for image recognition Deniz Yildiz Sofie Daniels, Felix Yang Luca Cavalli
13.03. #05. MobileNetV2: Inverted Residuals and Linear Bottlenecks Senthuran Kalananthan Andri Horat, Sofie Daniels Jonas Hein
13.03. #06. Attention Is All You Need Zhaochong An Anton Alexandrov, Jiugeng Sun Jonas Hein
13.03. #07. Learning Convolutional Neural Networks for Graphs Aidyn Ubingazhibov Oliver Lemke, Deniz Yildiz Denys Rozumnyi
20.03. #08. Dropout: a simple way to prevent neural networks from overfitting Oleh Kuzyk Hsiu-Chi Cheng, Aidyn Ubingazhibov Luca Cavalli
20.03. #09. Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation Oliver Lemke Ata Celen, Senthuran Kalananthan Jiaqi Chen
20.03. #10. FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search Maximilian Giang Benedikt Schesch, Andri Horat Fangjinhua Wang
27.03. #11. A Metric Learning Reality Check Felix Yang Elias Salameh, Ata Celen Shaohui Liu
27.03. #13. On Calibration of Modern Neural Networks Valentin Bieri Jiugeng Sun, Hsiu-Chi Cheng Dr. Hermann Blum
03.04. #14. Conditional Random Fields as Recurrent Neural Networks Jiugeng Sun Valentin Bieri, Oleh Kuzyk Linfei Pan
03.04. #15. Depth Map Prediction from a Single Image using a Multi-Scale Deep Network Hsiu-Chi Cheng Alexander Veicht, Shi Chen Zuria Bauer
03.04. #16. RAFT: Recurrent All-Pairs Field Transforms for Optical Flow Andri Horat Senthuran Kalananthan, Benedikt Schesch Rémi Pautrat
10.04. No Class
17.04. No Class
24.04. #17. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks Anton Alexandrov Yuqing Huang, Julian Sainz Martinez Boyang Sun
24.04. #18. A Style-Based Generator Architecture for Generative Adversarial Networks Elias Salameh Deniz Yildiz, Maximilian Giang Denys Rozumnyi
01.05. No Class
08.05. #19. ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases Shi Chen Zhaochong An, Gowtham Senthil Dr. Hermann Blum
08.05. #20. Emerging Properties in Self-Supervised Vision Transformers (DINO) Ata Celen Gowtham Senthil, Alexander Veicht Silvan Weder
15.05. #21. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis Alexander Veicht Aidyn Ubingazhibov, Valentin Bieri Zuoyue Li
15.05. #22. Convolutional Occupancy Networks Yuqing Huang Shi Chen, Elias Salameh Songyou Peng
22.05. #23. SuperPoint: Self-Supervised Interest Point Detection and Description Mathias Vogel Hüni Maximilian Giang, Anton Alexandrov Rémi Pautrat
22.05. #24. Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC Gowtham Senthil Oleh Kuzyk, Mathias Vogel Hüni Rémi Pautrat

© CVG, ETH Zürich webmaster: