Class time: Wednesday, 1:00 PM - 2:45 PM

Classroom: Dreese Lab 317

Course website: https://sites.google.com/view/osu-cse-5539-sp22-chao

Instructor: Prof. Wei-Lun (Harry) Chao https://sites.google.com/view/wei-lun-harry-chao

Email: chao.209@osu.edu

Office hour: Friday 9-10 am, using Carmen Zoom (see Carmen Canvas for the link)

Course abstract: This research course will cover various "advanced" machine learning (ML) and computer vision (CV) topics and their applications to perception for autonomous driving. Specifically, we will study ML topics such as domain adaptation, meta-learning, generative models, imbalanced learning, semi-supervised learning, self-supervised learning, etc.; CV topics such as object detection, instance/semantic segmentation, depth estimation, etc. We will then study how these techniques can be applied to perception problems in autonomous driving, which involves data captured by cameras, LiDAR, etc. The format of the class will be a mix of lectures and research paper presentations. Students who participate in this class are expected to be self-motivated graduate or senior undergraduate students.

Pre-requisites:

• Students are expected to have a decent degree of mathematical sophistication and to be familiar with linear algebra (Math 2568), multivariate calculus, probability, and statistics. Students are also expected to have knowledge of algorithm design and data structures. Students are expected to be able to code in Python.

• Students are expected to (self) learn deep learning software (e.g., Tensorflow and Pytorch).

• Students are expected to have a strong interest in machine learning, computer vision, and their applications in autonomous driving

• Students are expected to have taken courses in artificial intelligence/machine learning (3521/6521, 5523, or 5526) and/or computer vision (5524)

• Review materials can be found: linear algebra, probability, Python-1, Python-2, Python-3

Syllabus: Click

Grading (tentative):

• Participation: 5%

Participation includes attendance, asking questions, discussion in the lectures

• Paper presentation & survey (2 people): 45% (30%: presentation; 15%: survey)

The presentation is graded based on efforts and clearness in presenting the ideas of the papers. The survey report is graded based on efforts, clearness, and how well you organize the papers that you read. The report should include sections like introduction, background, approach, experiments, etc.

• Final project (1-3 people): 50% (10%: first presentation; 25%: final presentation (results); 15%: report)

First presentation: 5% for oral presentation, 5% for written first report (1-2 pages)

Required Textbook: No required textbook

Suggested references:

• Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. The MIT Press, 2012

• Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. The MIT Press, 2016

• Joel Janai, Fatma G¨uney, Aseem Behl, Andreas Geiger. Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art. Foundations and Trends in Computer Graphics and Vision, 2020

• Claudine Badue et al. Self-driving cars: A survey. Expert Systems With Applications, 2021

• Tutorials & workshop talks in CVPR, ICCV, ECCV, ICML, ICLR, and NeurIPS

Useful reference:

• Kaare Brandt Petersen and Michael Syskind Pedersen. The Matrix Cookbook

Announcements and communications:

• We will make announcements using the Carmen Canvas. Announcements of urgent matters will be mailed to your name.#@osu.edu address. If you do not regularly check those accounts, make sure you forward them to somewhere that you do.

• We will use Piazza for discussions. If you have questions about the course materials or policy, please also post them on these platforms. I will also monitor these discussions and answer as appropriate, but students should feel free to use the forums to have group discussions as well.

• Please only use email to contact the instructor for urgent or personal issues. Any e-mails sent to the instructor should include the tag "[OSU-CSE-5539]" in the subject line. (This ensures we can filter and prioritize your messages.) We reserve the right to forward any questions (and their answers) to the entire class if they should prove relevant. Please indicate if you wish to be anonymized (i.e. have your name removed) in this case.

Survey report:

• NeurIPS 2021 Latex style: https://neurips.cc/Conferences/2021/PaperInformation/StyleFiles

• Extend your paper presentation from 2-3 papers to 6-10 papers

• At least 8 pages, excluding reference (Introduction, an overview of the background, descriptions of some key algorithms and their concepts, and important experimental results and findings)

• Due day: 2 weeks after your presentation. Late reports will lead to an immediate 30% deduction on your report scores. If your report is late by a week, the deduction will become 60%. If your report is late by two weeks, you will get 0 points.

• The survey report is graded based on efforts, clearness, and how well you organize the papers that you read. The report should include sections like introduction, background, approach, experiments, etc.

• Example:

https://papers.nips.cc/paper/8420-failing-loudly-an-empirical-study-of-methods-for-detecting-dataset-shift.pdf

https://link.springer.com/article/10.1007/s10994-019-05855-6

Final project (comprehensive survey with experiments, individual project, or challenge: 1-3 people):

• Comprehensive topic studies: A team (or the whole class) selects a topic and performs a comprehensive survey of the techniques, datasets, and evaluation metrics. Then, the team is going to re-implement those techniques and re-evaluate on all the datasets with all the metrics. Students are encouraged to propose new techniques and experimental setups.

• Competition & challenges: A team (or the whole class) selects a competition & challenge held in top conferences and participates in it.

• Self-picked research topic: A team (or the whole class) selects a research topic. The expectation is to be ready to submit to a conference (e.g., NeurIPS 2022).

Example challenges:

• Learning from Imperfect Data (LID)

• https://sites.google.com/view/learning-with-limited-data

• Other suggestions from NeurIPS, ICML, ICLR, ICCV, ECCV, CVPR workshops

Week 1: PPT

Week 2: PDF

Week 3: PDF

Week 4: PDF, PPT
Week 5: PDF, PPT

Week 6: PPT, PDF
Week 7: PPT, PDF; Presentation: Link; Notes on Presentation and final project: PTT
Week 8: PPT, PDF; Presentation: PPT, PDF; Template: 1, 2
Week 9: PPT, PDF; presentation: PPT, PDF; final project: PDF

Week 10: PPT, PDF; presentation: PPT, PDF
Week 11: PPT, PDF; presentation: PPT, PDF
Week 12: PPT, PDF; presentation: PPT, PDF

Week 13: (forecasting) PPT, PDF; (weakly-supervised) PPT, PDF