16-824: Visual Learning and Recognition |
||
Spring 2022 |
||
This schedule is preliminary and subject to change as the term evolves.
Date | Topics | Course Materials | Instructor | Deadlines | |
Week 1 | |||||
Lecture 1 Wednesday 01/19/22 |
Introduction | Slides [CMU only] No Readings |
Deepak | ||
Week 2 | |||||
Lecture 2 Monday 01/24/22 |
Theories and History I | Slides [CMU only] Optional Readings: #1: Lecture 1, 2 (Svetlana Lazebnik's course) #2: William T. Freeman et.al. |
Deepak | ||
Lecture 3 Wednesday 01/26/22 |
Theories and History II | Optional Readings: Lecture 3, 4 (Svetlana Lazebnik's course) |
Deepak | ||
Week 3 | |||||
Lecture 4 Monday 01/31/22 |
Introduction to Data | Readings: #1: Alon Halevy, Peter Norvig, Fernando Pereira #2: Antonio Torralba, Alexei A. Efros #3: Timnit Gebru et.al. |
Deepak | ||
Lecture 5 Wednesday 02/02/22 |
Neural Networks | Readings: #1: Backpropagation: Olah and 231n #2: Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton |
Deepak | ||
Week 4 | |||||
Bonus Lecture TBD |
AWS/GCP and PyTorch Tutorial | AWS/GCP Tutorial[CMU only] Pytorch Tutorial[CMU only] |
TAs | HW1 out | |
Lecture 6 Monday 02/07/22 |
Convolutional Neural Network | Readings: #1: Karen Simonyan, Andrew Zisserman #2: Kaiming He et.al. |
Deepak | ||
Lecture 7 Wednesday 02/09/22 |
Recipes for Training Deep Networks | Readings: #1: Diederik P. Kingma, Jimmy Ba #2: Gao Huang, Zhuang Liu, et al. |
Deepak | ||
Week 5 | |||||
Lecture 8 Monday 02/14/22 |
Visualizing and Understanding Neural Nets | Readings: #1: Aravindh Mahendran, Andrea Vedaldi #2: David Bau, Bolei Zhou, et al. #3: Olah et al. |
Deepak | ||
Lecture 9 Wednesday 02/16/22 |
Attention and Transformers | Readings: #1: Ashish Vaswani et al. #2: Alexey Dosovitskiy et al. Optional Readings: #1: Sepp Hochreiter, et al #2: Thomas N. Kipf, Max Welling #3: Xiaolong Wang et al. |
Deepak | ||
Week 6 | |||||
Lecture 10 Monday 02/21/22 |
Image Segmentation | Readings: #1: Jonathan Long, Evan Shelhamer, Trevor Darrell #2: Kaiming He et al. #3: Olaf Ronneberger et al. |
Deepak | ||
Lecture 11 Wednesday 02/23/22 |
Object Detection | Readings: #1: Pedro F Felzenszwalb et.al. #2: Ross Girshick et.al. #3: Joseph Redmon et al. #4: Nicolas Carion et al. |
Deepak | HW1 due HW2 out |
|
Week 7 | |||||
Lecture 12 Monday 02/28/22 |
3D Image Understanding I | Readings: #1: Derek Hoiem, Alexei A. Efros, Martial Hebert #2: David Eigen, Rob Fergus #3: Georgia Gkioxari, Jitendra Malik, Justin Johnson |
Deepak | ||
Lecture 13 Wednesday 03/02/22 |
3D Image Understanding II | Readings: #1: Charles R. Qi*, Hao Su* et al. #2: Yue Wang et al. #3: Jeong Joon Park et al. |
Deepak | Project Proposal Due | |
Week 8 - Spring Break; No Classes | |||||
Week 9 | |||||
Lecture 14 Monday 03/14/22 |
3D Image Understanding III | Readings: #1: Kanazawa et al. #2: Hu et al. |
Deepak | ||
Lecture 15 Wednesday 03/16/22 |
Generative Models I | Readings: #1: Alec Radford, Luke Metz, Soumith Chintala #2: Diederik P Kingma, Max Welling #3: Diederik P. Kingma, Prafulla Dhariwal |
Deepak | ||
Week 10 | |||||
Lecture 16 Monday 03/21/22 |
Generative Models II | Readings: #1: Joshua B. Tenenbaum, William T. Freeman #2: Aditya Ramesh et al. #3: Phillip Isola et al. |
Deepak | ||
Lecture 17 Wednesday 03/23/22 |
Generative Models III | Readings: #1: Ho et al. #2: Nichol et al. |
Deepak | HW2 due HW3 out |
|
Week 11 | |||||
Lecture 18 Monday 03/28/22 |
Few-Shot and Transfer Learning | Readings: #1: Jeff Donahue et al. #2: Eric Tzeng et al. #3: Chelsea Finn et al. |
Deepak | ||
Lecture 19 Wednesday 03/30/22 |
Self-supervised Learning I | Readings: #1: Deepak Pathak et al. #2: Richard Zhang et al. #3: Jeff Donahue, Karen Simonyan |
Deepak | ||
Week 12 | |||||
Lecture 20 Monday 04/04/22 |
Self-supervised Learning II | Readings: #1: Ting Chen et al. #2: Kaiming He et al. #3: Aaron van den Oord, Yazhe Li, Oriol Vinyals |
Deepak | HW3 due | |
Lecture 21 Wednesday 04/06/22 |
Zoom/Remote Guest Lecture: NeRF, View Synthesis | Readings: #1: Adelson et al. #2: Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, et al. #3: Groueix et al. |
Pratul Srinivasan (Google) | HW4 out | |
Week 13 | |||||
Lecture 22 Monday 04/11/22 |
Action Recognition and Videos | Readings: #1: Karen Simonyan, Andrew Zisserman #2: Du Tran et al. #3: Joao Carreira, Andrew Zisserman |
Deepak | ||
Lecture 23 Wednesday 04/13/22 |
Zoom/Remote Guest Lecture: Human Pose Estimation | Readings: #1: Cao et al. #2: Carreira et al. |
Guest Lecture - Hanbyul Joo (SNU) | ||
Week 14 | |||||
Lecture 24 Monday 04/18/22 |
Mulitmodal Perception (Language/Sound/Touch/Action) | Readings: #1: Kelvin Xu et al. #2: Stanislaw Antol*, Aishwarya Agrawal*, et al. #3: Andrew Owens et al. #4: Roberto Calandra et al. |
Deepak | ||
Lecture 25 Wednesday 04/20/22 |
Towards Generalist Machines and Conclusion | Deepak | HW4 due | ||
Week 15 | |||||
Lecture 26 Wednesday 04/25/22 |
Course Project Presentation I | Students | Project presentations are due | ||
Lecture 27 Monday 04/27/22 |
Course Project Presentation II | Students | Project presentations are due | ||
Report Week | |||||
Monday 05/09/22 |
Project final reports are due |