Home     MCADS Lab     Research     Publications     Activities     Codes     Data     Teaching


CS 7180: Advanced Computer Vision


GENERAL INFORMATION

  • Instructor: Prof. Ehsan Elhamifar
  • Instructor Office Hours: TBA
  • Class: Mondays and Thursdays 11:45am—1:30pm, TBA
  • DESCRIPTION

    This course covers advanced research topics in computer vision. This class will prepare graduate students in both the theoretical foundations of computer vision as well as the practical approaches to building real Computer Vision systems. This course investigates current research topics in computer vision, including recognition, segmentation, summarization and detection tasks and with an emphasis on deep learning methods. We will examine data sources, features, and learning algorithms useful for understanding and manipulating visual data. Class topics will be pursued through lectures by the instructor, independent reading, class discussion and presentations, and state-of-the-art projects. The goal of this course is to give students the background and skills necessary to perform research in computer vision and its application domains such as robotics, healthcare and graphics. Students should understand the strengths and weaknesses of current approaches to research problems and identify interesting open questions and future research directions. Students will hopefully improve their critical reading and communication skills, as well.

    PREREQUISITES

    The emphasis of the course will be on recent advances in computer vision based on deep learning. Students must be familiar and have worked with deep neural networks, including CNNs. Students must also have taken a course on machine learning.

    SYLLABUS
    1. Visual data summarization: utility functions and scalable optimization

    2. Visual domain adaptation and generalization: unsupervised and semi-supervised methods

    3. Semantic image and video segmentation

    4. Recognition with less labeled data

    5. Generative adversarial networks

    6. Neural architecture search and network pruning

    7. Vision for embodied agents

    8. Fairness in computer vision

    GRADING

    The first lectures will be delivered by the instructor. The remaining lectures will consist of presentations of papers by students and in-class discussions. Each student needs to read the papers for the upcoming lecture, write and submit a report before the lecture. In addition, each student will work on a project, which will be presented at the end of the semester. The grading will be based on the reports, participation in discussions and class project.

    ETHICS

    All students in the course are subject to the Northeastern University's Academic Integrity Policy. Any submitted report/homework/project by a student in this course for academic credit should be the student's own work. Collaborations are only allowed if explicitly permitted. Per CCIS policy, violations of the rules, including cheating, fabrication and plagiarism, will be reported to the Office of Student Conduct and Conflict Resolution (OSCCR). This may result in deferred suspension, suspension, or expulsion from the university.