EECS 542: Advanced Topics in Computer Vision

Instructor:	Jason Corso (jjcorso)
Time/Place:	F 1500-1800 in 1670 BBB
Office Hours:	see webpage
Syllabus:	here

---

Course Description

The course will focus on learning structured representations and embeddings for high-level problems in computer vision. Approaches for structured prediction, deep learning, and dictionary learning will be covered, all with an emphasis on modeling certain classes of structure, such as affine invariance and sparsity. The course will be highly interactive with a mix of readings, homeworks, quizzes and a course project.

Each week will emphasize a particular topic in this area through a foundational reading, an application reading, a (small) problem-set, and a quiz. Three-to-four longer term group homeworks will be assigned during the term to allow for deeper inquiry. Finally, one project will be conducted near the end of the term.

The course uses engaged learning with an emphasis on active, asynchronous individual and team-based learning. Evaluation is largely through effort and team-engagement rather than classical scoring. The course will be both fun and intellectually rewarding.

Course Goals

Provide a deep dive into high-level computer vision with both theoretical and practical topics. Students will also learn how to read academic papers. Students will gain practical experience with modern computer vision systems, languages, tools, and environments.