Chenliang Xu

pic

Spring 2023 - CSC 577: Advanced Topics in Computer Vision

Basic Information

Meet Time & Location: Tue/Thu 09:40-10:55 in Hylan 203

Instructor: Prof. Chenliang Xu
Office Hours: Tue 11:00-noon in Wegmans 3005

Information Flow: We will use Blackboard to make class announcements, host lecture notes, and post and grade assignments. We will use Blackboard's Discussion Board for course-related discussion and Q&A. You can expect to get faster help from your classmates, besides the teaching team. However, feel free to email me or the TAs if it is about a personal matter. Finally, this Course Website containing a course schedule serves as the syllabus.


Course Description

This course covers advanced research topics in computer vision with an emphasis on learning structured representations and embeddings. Approaches for learning from unimodal (e.g., images and videos), and multimodal data (e.g., vision and language, vision and audio) will be covered and include topics from structured predications, deep learning and others. The course will be a mix of lecture, student presentation and discussion.

Course Objectives: PhD Students: gain research experience in computer vision; MS Students: get prepared for a software engineer career in computer vision and artificial intelligence.

Prerequisites: Machine Vision or Machine Learning or Deep Learning or permission of the instructor.


Schedule

The course schedule will be populated over the term.
Theme 1: Learning Trustworthy Representations
Theme 2: Vision-and-Language, 3D Vision
Theme 3: Videos, Graphs in Vision
Format: (Background Presenter (B), Discussion Leader (D))

Dates Tuesday (T) Thursday (R) Notes
1/10,12 No Class: Before Term Overview
1/17,19 2-minute Madness Paper Talks Vision Transformer
(instructor-led)
1/24,26 ConvNet 2020s
(B: Rongyi, D: Luchuan)
Self-Supervised ViT
(B: Susan, D: Will)
1/31,2/2 Sanity Checks
(B: Zeliang, D: Anton)
Class Selectivity
(B: Anton, D: Rongyi)
2/7,9 Learning Cloud Computing
(by Jing Bi)
Transferable Attacks
(B: Zeliang, D: Zichen)
2/14,16 Project Proposal Diffusion Counterfactuals
(B: Andy, D: Zeliang)
2/21,23 CLIP
(B: Jinsheng, D: Susan)
Distribution Shifts
(B: Anton, D: Jinsheng)
2/28,3/2 CLIP for Open-Vocab. Detection
(B: Will, D: Andy)
CLIP for Domain Adapation Gen.
(B: Luchuan, D: Zichen)
3/7,9 Spring Break Spring Break ICCV ddl
3/14,16 Cancelled DiffusionDet
(B: Zhuo, D: Andy)
3/21,23 Bundle-Adjusting NeRF
(B: Susan, D: Zichen)
CLIP for NeRF
(B: Rongyi, D: Luchuan)
Mid-term Project
Video Presentations
3/28,30 Stylized NeRF
(B: Luchuan, D: Susan)
Object States and Actions
(B: Will, D: Zhuo)
4/4,6 Object States and Actions
(B: Andy, D: Will)
Connecting Views
(B: Zichen, D: Jinsheng)
4/11,13 Neural-Symbolic Reasoning for VRD
(B: Zhuo, D: Anton)
Graphs for Video Objects
(B: Rongyi, D: Zhuo)
4/18,20 Cross-Model Pseudo-Labeling
(B: Jinsheng, D: Zeliang)
Final Project Presentation I
(Susan, Luchuan, Will, Zichen, Andy)
4/25,27 Final Project Presentation II
(Jinsheng, Zeliang, Rongyi, Anton, Zhuo)
No Class: Term Finished

Course Work and Evaluation


Other Policies

Code of Conduct: Check here for classroom "etiquette" expectations.

Academic Honesty: All assignments and activities associated with this course must be performed in accordance with the University of Rochester's Academic Honesty Policy. More information is available here. You are expected to read, understand, and follow the policy.

Disabilities: Please see me about your required accommodations as early as possible in the term. The University of Rochester respects and welcomes students of all backgrounds and abilities. In the event you encounter any barrier(s) to full participation in this course due to the impact of a disability, please contact the Office of Disability Resources. The access coordinators in the Office of Disability Resources can meet with you to discuss the barriers you are experiencing and explain the eligibility process for establishing academic accommodations. You can reach the Office of Disability Resources at: disability@rochester.edu; (585) 276-5075; Taylor Hall; link.

Accommodations for COVID-Related Illness: Please let me know asap. At the same time, You should contact the College Center for Advising Services (CCAS) or the Graduate Education and Postdoctoral Affairs office. These offices will be able to assist you and refer you to the right resources.