CS2770: Computer Vision, Spring 2025
Location (class): IS 405
Class time: Monday and Wednesday, 9:30am - 10:45am
Instructor: Nils Murrugarra (email: nem177 AT pitt DOT edu; use “[CS 2770]” at the beginning of the subject line)
Instructor’s office hours: Mon 11am - 1pm and Tue 9am-11am
Instructor’s office: Sennott Square 5419
TA: Cagri Gungor ( cagri.gungor AT pitt DOT edu )
TA’s office hours: Wed 12-2 pm @ zoom, Th 4-5pm @ SENSQ 5501
Canvas: used for announcements and assignment submission
Schedule
| Date | Chapter | Slides | Homework |
|---|---|---|---|
| 01/08 | Intro | Intro_course [pdf] [pptx] Supp: Linear_algebra [pdf] [pptx] |
|
| 01/13 | Intro_cv [pdf] [pptx] | ||
| 01/15 | Low-level Vision | Filters and Texture [pdf] [pptx] | |
| 01/20 | No Class | ||
| 01/22 | Filters and Texture | ||
| 01/27 | Features [pdf] [pptx] | A1 on canvas | |
| 01/29 | Grouping [pdf] [pptx] | ||
| 02/03 | High-level Vision | Intro to Recognition [pdf] [pptx] | |
| 02/05 | Intro to Recognition | ||
| 02/10 | Convolutional Neural Networks [pdf] [pptx] | A2 on canvas | |
| 02/12 | Convolutional Neural Networks | ||
| 02/17 | Convolutional Neural Networks | ||
| 02/19 | Object Recognition and Image Segmentation [pdf] [pptx] | ||
| 02/24 | Exam 1 | ||
| 02/26 | No Class. Please, work on your project proposal and assignments. | ||
| 03/03 | No Class. Spring Break. | ||
| 03/05 | No Class. Spring Break. | ||
| 03/10 | Object Recognition and Image Segmentation | ||
| 03/12 | Object Recognition and Image Segmentation | A3 on canvas | |
| 03/17 | Sequential Data [pdf] [pptx] | ||
| 03/19 | Sequential Data | ||
| 03/24 | Sequential Data | ||
| 03/26 | Generative Models [pdf] [pptx] | A4 on canvas | |
| 03/31 | Project Development | ||
| 04/02 | Generative Models | ||
| 04/07 | Conditional Generative Models [pdf] [pptx] | ||
| 04/09 | Conditional Generative Models | A5 on canvas | |
| 04/14 | Large Language Models [pdf] [pptx] | ||
| 04/16 | Multimodal Large Language Models [pdf] [pptx] | ||
| 04/21 | Guest Lecture. Unlocking Compositional Reasoning in Vision-Language Models Paola Cascante-Bonilla, Research Assistant Professor @ Stony Brook University. [pdf] |
||
| 04/23 | Retrieval Augmented Generation (RAG) for LLMs [pdf] [pptx] | ||
| 04/28 | Project Presentations | ||
| 04/30 | Project Presentations |