The abridged syllabus you’re looking for has not been entered yet. We’ve provided a similar abridged syllabus as an example. Check back later for that specific abridged syllabus. The complete syllabus will be available in your Canvas course.

525.733.8VL - Deep Learning for Computer Vision

Electrical and Computer Engineering

Spring 2024

Description

Recent technological advances coupled with increased data availability have opened the door for a wave of revolutionary research in the field of Deep Learning. In particular, Deep Neural Networks (DNNs) continue to improve on state-of-the-art performance in many standard computer vision tasks including image classification, segmentation, object recognition, object localization, and scene recognition. With an emphasis on computer vision, this course will explore deep learning methods and applications in depth as well as evaluation and testing methods. Topics discussed will include network architectures and design, training methods, and regularization strategies in the context of computer vision applications. Following a seminar format, students will be expected to read, understand, and present recent publications describing the current state-ofthe-art deep learning methods. Additionally, team projects will give students an opportunity to apply deep learning methods to real world problems.Prerequisite(s): Students should have taken courses in computer vision and machine learning/pattern recognition, have basic familiarity with OpenCV, Python and C++, as well as prior class instruction in neural networks.

Instructor

Nasser Nasrabadi

Course Structure

The course consists of lectures with discussions, reading assignments (technical papers), one mid-term, one extensive final project and 8 homework assignments using dedicated neural network software such as Pytorch, Tensor Flow, Caffe or Matlab. Each student will carry out one independent mid-term mini-project and a final project in an area subject to the instructor's approval.

Course Topics

See Course Outline

Course Goals

The purpose of this graduate course is to provide the fundamental set of techniques and advanced architectures that constitute deep learning as of today, while providing a thorough grounding in the methodologies and mathematical foundations.

Course Learning Outcomes (CLOs)

Understand the modern CNN-based architectures (i.e., LeNet, AlexNet, VGGNet, GooGleNet, ResNet, DenseNet, HighwayNet, and FractalNet).
Describe relative merits of various deep learning architectures (i.e., CNN, GAN, Cycle GAN, and LSTM).
Explain auto-encoders for feature extraction, dimensionality reduction and manifold representation.
Use of regularization for network sparsity.
To be able to use advanced deep learning frameworks for object recognition, pedestrian detection, face, iris, fingerprint identification.

Textbooks

Class Notes will be provided
Journal & Conference papers will be assigned for HWs and class Projects

Other Materials & Online Resources

“Deep Learning” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press, Nov 18, 2016, ISBN:0262035618, 9780262035613.

Student Coursework Requirements

Homework Assignments (8 in total equal points): 30%
• Mid-term Project (assignment for midterm, 15-minute oral presentation): 30%
• Final Project (student will read tech. paper and implement with 15-minute oral presentation): 40%

Homework: There will be 30% credits for 8 homework assignments. Typically, problems will be assigned in class or Emailed. These assignments are to help you determine your level of mastery of knowledge presented in class.

Projects: There are two project. One midterm-project and one extensive final project to be presented to the class. The projects will require performing literature search on research topics, understanding technical papers, implement and exploring new solutions.

Project Dates: Dates for the two projects are shown in the class schedule. Any date changes will be finalized in class. In case you miss a class, make sure you stay in touch with important announcements.

Grading Policy

90 ≤ A ≤ 100
80 ≤ B < 90
70 ≤ C < 80
60 ≤ D <
70 F < 60

Course Policies

General: Attendance at lecture is expected. If you miss a class, you are responsible for all assignments and material covered. You are required to participate in all class discussions. You will be required to answer questions or discuss your solutions in class. You must maintain good class notes and should review past materials covered before attending a class.

Help Session: If you attended the lectures and did not understand any material, see the instructor promptly – before the next lecture. If you did not attend the class, first obtain the notes from your classmates, review the material, and then see your instructor for further clarification.

Attendance Policy: Consistent with JHU guidelines, students absent from regularly scheduled project presentation because of authorized University activities will have the opportunity to take them at an alternate time. Make-up project presentation for absences due to any other reason will be at the discretion of the instructor.

Academic Policies

Deadlines for Adding, Dropping and Withdrawing from Courses

Students may add a course up to one week after the start of the term for that particular course. Students may drop courses according to the drop deadlines outlined in the EP academic calendar (https://ep.jhu.edu/student-services/academic-calendar/). Between the 6th week of the class and prior to the final withdrawal deadline, a student may withdraw from a course with a W on their academic record. A record of the course will remain on the academic record with a W appearing in the grade column to indicate that the student registered and withdrew from the course.

Academic Misconduct Policy

All students are required to read, know, and comply with the Johns Hopkins University Krieger School of Arts and Sciences (KSAS) / Whiting School of Engineering (WSE) Procedures for Handling Allegations of Misconduct by Full-Time and Part-Time Graduate Students.

This policy prohibits academic misconduct, including but not limited to the following: cheating or facilitating cheating; plagiarism; reuse of assignments; unauthorized collaboration; alteration of graded assignments; and unfair competition. Course materials (old assignments, texts, or examinations, etc.) should not be shared unless authorized by the course instructor. Any questions related to this policy should be directed to EP’s academic integrity officer at ep-academic-integrity@jhu.edu.

Students with Disabilities - Accommodations and Accessibility

Johns Hopkins University values diversity and inclusion. We are committed to providing welcoming, equitable, and accessible educational experiences for all students. Students with disabilities (including those with psychological conditions, medical conditions and temporary disabilities) can request accommodations for this course by providing an Accommodation Letter issued by Student Disability Services (SDS). Please request accommodations for this course as early as possible to provide time for effective communication and arrangements.

For further information or to start the process of requesting accommodations, please contact Student Disability Services at Engineering for Professionals, ep-disability-svcs@jhu.edu.

Student Conduct Code

The fundamental purpose of the JHU regulation of student conduct is to promote and to protect the health, safety, welfare, property, and rights of all members of the University community as well as to promote the orderly operation of the University and to safeguard its property and facilities. As members of the University community, students accept certain responsibilities which support the educational mission and create an environment in which all students are afforded the same opportunity to succeed academically.

For a full description of the code please visit the following website: https://studentaffairs.jhu.edu/policies-guidelines/student-code/

Classroom Climate

JHU is committed to creating a classroom environment that values the diversity of experiences and perspectives that all students bring. Everyone has the right to be treated with dignity and respect. Fostering an inclusive climate is important. Research and experience show that students who interact with peers who are different from themselves learn new things and experience tangible educational outcomes. At no time in this learning process should someone be singled out or treated unequally on the basis of any seen or unseen part of their identity.

If you have concerns in this course about harassment, discrimination, or any unequal treatment, or if you seek accommodations or resources, please reach out to the course instructor directly. Reporting will never impact your course grade. You may also share concerns with your program chair, the Assistant Dean for Diversity and Inclusion, or the Office of Institutional Equity. In handling reports, people will protect your privacy as much as possible, but faculty and staff are required to officially report information for some cases (e.g. sexual harassment).

Course Auditing

When a student enrolls in an EP course with “audit” status, the student must reach an understanding with the instructor as to what is required to earn the “audit.” If the student does not meet those expectations, the instructor must notify the EP Registration Team [EP-Registration@exchange.johnshopkins.edu] in order for the student to be retroactively dropped or withdrawn from the course (depending on when the "audit" was requested and in accordance with EP registration deadlines). All lecture content will remain accessible to auditing students, but access to all other course material is left to the discretion of the instructor.