Lectures (preliminary schedule)

Assignments

While the assignments add points to the final grade, their primary goal is to prepare you for the project. The first assignment is to set up a general training framework that lets one experiment with different datasets, neural network architectures, and objective functions. This framework will be extended and used in the remaining two assignments and also the final project. Instead of step-by-step instructions, exercises are posed as high-level tasks. Questions are set up to train independent thinking, which is integral to solving actual problems in research and industry settings. This does not mean that you are without support; you are highly encouraged to search online and consult the abundance of deep learning tutorials as a basis for your solution. Furthermore, office hours are set up to provide personal assistance.

Academic Integrity. Assignments must be solved individually using the available course material and other online sources. You are neither allowed to copy nor look at parts of any of the assignments from anyone else. Accordingly, it is not allowed to post solutions online or distribute them in (private) forums. The university policies on academic integrity are rigorously applied.

Submission. Solutions must be handed in through the Canvas system and be kept private.

Deadline and grading. Assignments will be due on the dates specified in the schedule, always at 11:59 pm PST. A late submission by one day will still be accepted but reduces the score by -25%. The grading is based on correctness and completeness, as detailed in each exercise description.

Research papers

The second half of the course will constitute a reading group, focussing on seminal and latest research. Each student will write reviews every week and is expected to participate actively in the discussion, along with presenting once during the course. Preferences will be considered for the presentation topic assignment.

Reviews. All students are expected to read one of the two papers that will be presented and discussed in each class. Nevertheless, it is recommended to at least skim through both the papers. Each presentation will be followed by an in-depth discussion on technical aspects, relations to other works, and practical utility. To initiate and start new arguments, a short review of the selected paper will have to be submitted, on the day before the class. Try to raise non-obvious aspects with the following:

• A summary of the main contribution
• One question that is well suited for discussion
• One strength
• One weakness

These reviews will be distributed across all course participants. Keep your review concise (less than half a page) and self-contained.

Presentation. The presentation should be compact and precisely 20 minutes long. Focus on the most crucial points, those needed to understand the content, novelty, and impact of the given work. Most importantly, draw links to previous presentations, lecture content, and the related work you know. Such an embedding into a broader context will make your presentation unique and stimulating, especially for those who have read the underlying paper in detail. You can take the paper illustrations and other available online material, such as videos supplementing the paper, as a basis for your presentation, as long as you reference the source adequately on each slide. You will be the expert and be required to study the paper in sufficient depth to answer questions and trigger a rich discussion. Practice your talk before, ideally in front of a small audience, to get the timing and the messages right. Note that a part of your audience will have read the paper in detail and others will only have skimmed through. Therefore, try to address experts and newcomers alike. The tutor will assist you in this and give feedback on your planned presentation once.

• The review must be submitted on the evening before the class, by 11:59 pm via Canvas. Missing out on a total of two reviews will be tolerated. Full points for a review are given if all four of the above-listed bullet points are answered. On the day of your presentation, send in your sldies exported as PDF instead of the review (see below).
• The presentation slides must be handed in and be discussed with the tutor latest by two working days before the presentation. It is your responsibility to set up a meeting (~30 min duration) with the TA in advance. This session is to your own benefit and will not be graded. Submit your final slides on Canvas, the Slide upload/Presentation Assignment.
• Presentation. Arrive early on the day of your presentation and ensure that you have all the necessary equipment with you and that your presentation runs smoothly. We grade the presentation based on quality, talk structure, and the context established to related work.

Project

The whole course is structured to prepare for the final research project. The goal is to either extend an existing approach, combine existing tools for solving a new problem, or to come up with an entirely new algorithm. Some topics and open research problems are given in class, but we highly encourage you to come up with your own idea on the basis of your unique background and experience. Projects can deviate from the core lecture topics, as longs as they are within CG, CV, and ML. You are encouraged to work in groups of two. Joining forces will allow you to complement your strengths and work on more challenging and rewarding problems. Nevertheless, both of you must have unique responsibilities, which have to be explicitly listed, and be involved in all of the following project stages:

• Project proposal. You must deliver a 3-minute pitch and an accompanying written plan (one page, 11pt font). The proposal must cover the research idea, the possible algorithmic contributions, and an outline of the evaluation.
• Literature review. Study the most related work. For instance, you can start with those papers discussed in class that are similar to your task, and search for more papers that cite and are cited by them. Google Scholar has the appropriate tools for that. This will form the base of your related work section.
• Development and coding. Make use of the frameworks developed during the course assignments and utilize other online sources as a basis. The project is not meant to re-invent the wheel but to develop something new on top of the existing works. The code must be submitted alongside the report, and your contributions and the places from where the remaining parts are taken must be documents in the code and report.
• Evaluation. Design and run experiments that validate the correctness of your contribution and, ideally, show qualitative or quantitative improvements on existing solutions. Showing that an approach does not work well can also be a contribution, but is generally harder to get "waterproof".
• Report writing. In an case, the report becomes an expanded version of the proposal plan that fills out the motivation, related work, method description, and evaluation sections. It should follow the overall structure of a research paper and be 8 pages long in the double-column format of CVPR [link]. Start early on the writing, e.g., compile the related work section while you do the literature review. Writing is an incremental process that requires many iterations until the outcome is mathematically sound, is explained clearly, and reads well.
• Supplemental document (optional). In case the 8 pages are insufficient, proofs and implementation details can be given in an appendix, and a video can be submitted to give additional qualitative results in motion. However, the main report must remain self-contained.

Project proposal, pitch, report, and final presentations will be due on the dates and times specified in the schedule above (proposal and pitch before the mid-term break, presentations in the last two weeks, submitting the report on the last day of classes). A late submission of one day reduces the gained points by -25%. The grade will mainly depend on the project definition, how well you present them in the report, how distinctly you position your work in the related literature, how thorough your experiments are, and how thoughtfully your contribution is derived.