Course 2018
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.
The seminar will start with introductory lectures to provide (1) a compact overview of challenges and relevant machine learning and deep learning research, and (2) a tutorial on critical analysis and presentation of research papers. Each student then chooses one paper from the provided collection to present during the remainder of the seminar. The students will be supported in the preparation of their presentation by the seminar assistants.
News
- 20 February: All the slides from the first session are online.
- 19 February: The introductory slides from today's session are online. Rest will follow soon.
- 2 February: The preliminary schedule and paper selection are online!
Important information
The students will present one paper each. However, they are 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. The student will be graded based on both their presentation (80%) and their participation in the assigned discussions (20%).
Attendance is required to pass the course (3 absences allowed).
Slides
Schedule (Tentative)
| Date |
Topic |
Presenter |
Critics |
Assistant |
| 19.2. |
Introduction |
|
|
|
| 26.2. |
ImageNet: A Large-Scale Hierarchical Image Database |
R. Brügger |
I. Beloshapka |
D. Thul |
| 5.3. |
Playing for Data: Ground Truth from Computer Games |
R. Sivanesan |
S. Häfeli,
V. Vitchevsky |
I. Cherabier |
| 12.3. |
Learning representations by back-propagating errors |
S. Häfeli |
R. Brügger,
G. Tong |
I. Cherabier |
|
ImageNet Classification with Deep Convolutional Neural Networks |
G. Tong |
A. Oertel,
M. Gupta |
L. Koch |
| 19.3. |
Backpropagation applied to handwritten zip code recognition |
I. Beloshapka |
M. Gupta,
R. Sivanesan |
D. Thul |
|
Deep sparse rectifier neural networks |
I. Stanojkovic |
A. Dhall,
L. Göller |
V. Tsiminaki |
|
Multi-Scale Context Aggregation by Dilated Convolutions |
S. Woerner |
S. Häfeli,
X. Huang |
L. Koch |
| 26.3. |
Generative Adversarial Networks |
H. Wang |
Y. Chen,
I. Stanojkovic,
V. Vitchevsky |
V. Tsiminaki |
| 9.4. |
Dropout: a simple way to prevent neural networks from overfitting |
M. Gupta |
A. Dhall,
N. Gosala,
S. Curry |
A. Cohen |
| 23.4. |
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks |
Y. Chen |
R. Brügger,
N. Gosala,
R. Sivanesan |
Z. Cui |
|
You Only Look Once: Unified, Real-Time Object Detection |
A. Dhall |
L. Jendele,
I. Stanojkovic,
I. Beloshapka |
A. Cohen |
| 30.4. |
Visualizing and Understanding Convolutional Networks |
N. Gosala |
Y. Chen,
H. Wang |
A. Cohen |
|
Fully convolutional networks for semantic segmentation |
S. Curry |
Y. Wang,
R. Deuber |
Z. Cui |
| 7.5. |
Going Deeper with Convolutions |
A. Oertel |
G. Tong,
S. Curry |
D. Thul |
| 14.5. |
Spatial Transformer Networks |
X. Huang |
L. Saouma |
K. Tóthová |
|
Dynamic Routing Between Capsules |
V. Vitchevsky |
A. Oertel,
L. Jendele |
L. Koch |
| 28.5. |
Conditional Random Fields as Recurrent Neural Networks |
L. Saouma |
X. Huang,
S. Woerner,
H. Wang |
L. Koch |
|
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks |
L. Jendele |
L. Saouma,
S. Woerner |
A. Cohen |
|
