Advanced Techniques in Visual Learning & Recognition

CMSC828I - Fall 2019 · Unive-remove-rsity of Maryland

Overview

A graduate-level course in computer vision, with an emphasis on high-level recognition tasks. We will read an eclectic mix of classic and contemporary papers on a wide-range of topics. The course structure will combine lectures, student presentations, in-class discussions, and a course project. The goal of this course is to:

  1. Become knowledgeable about how a particular sub-topic evolved, the state-of-the-art, and the challenges that need to be addressed.
  2. Develop skills to critically read, analyze, and present a body of research.
  3. Learn to draw connections between different works and engage in productive discussions.

Prerequisites

While there are no formal prerequisites for this course, familiarity with introductory courses in computer vision (CMSC426 or similar) and machine learning (CMSC422 or similar) is assumed. If you have not taken courses covering this material, consult with the instructor. Note that a basic knowledge of linear algebra, probability, and calculus is required.

Logistics

Where & when

ATL 1113
Monday, Wednesday 12:30pm - 1:45pm

Instructor

Abhinav Shrivastava
4238 IRB
abhinav@cs.umd.edu
Office hours: TBD.

Teaching Assistant

Jack Rasiel
Office hours: by email appointment.

Quick Links

Piazza
Web Accessibility
CMSC828I Fall 2018

Schedule

Coming soon!


Date Presenter Topic Readings Slides Notes
I – Background and Foundations
Aug 27 Abhinav Introduction to the class
slides
Aug 29
Quiz


Sep 3 Abhinav Introduction to Data
slides
Sep 5 Abhinav Data-driven methods in vision I
slides
Sep 10 Abhinav Data-driven methods in vision II
(+ some background material)

slides
Sep 12
Sep 17
Abhinav ConvNets and Architectures Important Architectures:
What goes on inside a CNN?
slides
II – Core Tasks
Sep 19
Sep 24
Abhinav Two foundational tasks:
  • Object Detection
  • Image Segmentation
Background - Object Detection:
Background - Segmentation:
Single-stage object detection:
slides
Sep 26
Oct 1
Abhinav Two foundational tasks:
  • Object Detection
  • Image Segmentation
Semantic Segmentation:
Object Proposals:
Multi-stage object detection:
Multi-stage detection & instance segmentation:
An awesome overview of recent detection methods -- MMDetection; arXiv 2019
slides
Oct 3
Oct 8
Abhinav Two foundational tasks:
  • Object Detection
  • Image Segmentation
Architectures:
Analysis and diagnosis:
Training:
slides
Oct 10
Oct 15
Abhinav Introduction to other tasks;
Human Pose Estimation
Background Reading:
Readings:
slides
Oct 17
Mid-term exam


III – Advanced Tasks
Oct 15
Oct 22
Nov 5
Abhinav
Pirazh
Pulkit
Action Recognition Background:
Primary Readings:
Additional Readings:
Additional Readings (tasks and architectures):
slides

student slides

Oct 24
No Class
Oct 29 Jack
Susmija
Chayan
Raghav
Nantha
Shihao
Niket
Pranav
Kartik
Embodied visual perception (vision + action) Primary readings: Additional readings: slides

student slides

Oct 31 Jack
Hrishikesh
Mucong
Nikhil
Naman
Ruoyu
Adheesh
Stephanie
Koutilya
Intuitive Physics Primary readings: Additional readings:
slides

student slides

Nov 5 Abhinav
Ishita
Tao
Saumya
Alex
Rachith
Utkarsh
Shishira
All about 3D:
  • 3D Scene Understanding - Primitives and Reasoning
  • Objects + 3D
Background:
Required readings:
Additional and background readings: Great resource for 3D-related papers: 3D Machine Learning
slides

student slides

Nov 7 Abhinav
Krishna
Ping
Saksham
Mara
Mansi Goel
Trisha
Geng
Beyond Labeled Datasets I:
  • Weakly, Semi Supervised Learning
  • Learning from the Web
Required readings: Additional and background readings: student slides
Nov 12 Abhinav
Aditya
Ashwin
Shlok
Goonwanth
Matt
Abhishek
Jiaye
Hanyu
Assortment:
  • Context Reasoning
  • Attributes and Fine-grained Recognition
  • Zero-shot, Few-shot/low-shot
Primary Readings: Background and Additional Readings: slides

student slides

Nov 14
No Class - CVPR DEADLINE
Nov 19
Dec 6
Abhinav Generative Models GANs: VAEs: slides
Nov 21 Abhinav
Sigurthor
Saimouli
Yexin
Sharath
Tianrui
Utsav
Gaurav
Kapil
Pradeep
Generative Models
Self-Supervised Learning
Assortment of Image Generative Models: Assortment of Self-Supervised Learning Papers: (above)

student slides

Nov 26 Abhinav
Dylan
Eleftheria
Puneet
Nirat
Vamshi
Rishabh
Vision + Language/text Easier tasks: Tasks: Sampling of methods: student slides
Nov 28
Thanksgiving Break


VI – Misc. + Epilogue
Dec 3-5 No Class


Dec 6 Abhinav Visual data mining and discovery Required readings: Additional readings: slides
Dec 6
Ethics & Bias
Epilogue



Dec 12
Final Project Presentations SPH 1301
3:00pm – 7:00pm


Dec 16
Final Exam ATL 1113
1:30pm – 3:30pm


Syllabus

Grading and collaboration

Grading Breakdown

  • [20%] Class Participation
  • [15%] Class Presentation
  • [30%] Research Project (presentation and report):
    • Proposal (2 pages)
    • Final presentation (a few minutes)
    • Final report (4-5 pages, CVPR style)
  • [35%] Exams:
    • 1 Background Quiz
    • 1 Mid-term
    • 1 Final

Collaboration

Unless otherwise stated, assume that the UMD Code of Academic Integrity applies.

Submitting project reports, format, etc.

Details will be announced in class.

Notes

Syllabus subject to change.

Accommodations and Policies

Academic Integrity

Note that academic dishonesty includes not only cheating, fabrication, and plagiarism, but also includes helping other students commit acts of academic dishonesty by allowing them to obtain copies of your work. In short, all submitted work must be your own. Cases of academic dishonesty will be pursued to the fullest extent possible as stipulated by the Office of Student Conduct. It is very important for you to be aware of the consequences of cheating, fabrication, facilitation, and plagiarism. For more information on the Code of Academic Integrity or the Student Honor Council, please visit http://www.shc.umd.edu.

Excused Absence and Academic Accommodations

Any student who needs to be excused for an absence from a single lecture, recitation, or lab due to a medically necessitated absence shall:

  1. Make a reasonable attempt to inform the instructor of his/her illness prior to the class.
  2. Upon returning to the class, present their instructor with a self-signed note attesting to the date of their illness. Each note must contain an acknowledgment by the student that the information provided is true and correct. Providing false information to University officials is prohibited under Part 9(i) of the Code of Student Conduct (V-1.00(B) University of Maryland Code of Student Conduct) and may result in disciplinary action.
  3. This self-documentation may not be used for the Major Scheduled Grading Events as defined below.

Any student who needs to be excused for a Major Scheduled Grading Event, must provide written documentation of the illness from the Health Center or from an outside health care provider. This documentation must verify dates of treatment and indicate the time frame that the student was unable to meet academic responsibilities. No diagnostic information shall be given. The Major Scheduled Grading Events for this course include midterm and final exam. For class presentations, the instructor will help the student swap their presentation slot with other students.

It is also the student's responsibility to inform the instructor of any intended absences from exams and class presentations for religious observances in advance. Notice should be provided as soon as possible, but no later than the Monday prior to the the midterm exam, the class presentation date, and the final exam.

Any student eligible for and requesting reasonable academic accommodations due to a disability is requested to provide a letter of accommodation from the Office of Disability Support Services within the first three weeks of the semester.

Other Accommodations and Policies

You can find the university’s course policies here.