16-824: Visual Learning and Recognition |
||
Spring 2025 |
||
Tuesday and Thursday, 3:30-4:50pm, DH A302 |
Date | Topics | Course Materials | Instructor | Deadlines | |
Week 1 | |||||
Lecture 1 Tuesday 01/14/25 |
Introduction |
No Readings |
Shubham | ||
Lecture 2 Thursday 01/16/25 |
History & Theories |
No Readings |
Shubham | ||
Week 2 | |||||
Lecture 3 Tuesday 01/21/25 |
Data |
Readings: #1: Alon Halevy, Peter Norvig, and Fernando Pereira #2: Antonio Torralba & Alexei A. Efros #3: Chen Sun et al. #4: Timnit Gebru et al. |
Shubham | ||
Bonus Lecture Wednesday 01/22/25 |
AWS and PyTorch Tutorial | Nikhil | |||
Lecture 4 Thursday 01/23/25 |
CNNs |
Readings: #1: Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton #2: Karen Simonyan, Andrew Zisserman #3: Kaiming He et.al. #4: Zhuang Liu et al. |
Shubham | ||
Week 3 | |||||
Lecture 5 Tuesday 01/28/25 |
Visualizing & Understanding NNs |
Readings: #1:Aravindh Mahendran, Andrea Vedaldi #2: David Bau, Bolei Zhou, et al. #3: Ramprasaath R. Selvaraju et al. #4: Olah et al. |
Shubham | ||
Lecture 6 Thursday 01/30/25 |
Transformers I |
Readings: #1: Ashish Vaswani et al. #2: Ilya Sutskever, Oriol Vinyals, Quoc V. Le #3: Dzmitry Bahdanau, KyungHyun Cho, Yoshua Bengio Optional Readings: #4: Sepp Hochreiter, et al |
Shubham | HW1 Out (Classification + Detection) | |
Week 4 | |||||
Lecture 7 Tuesday 02/04/25 |
Transformers II |
Readings: #1: Alexey Dosovitskiy et al. #2: Ze Liu et al. #3: Andrew Jaegle et al. Optional Readings: #4: Ilya Tolstikhin et al. |
Shubham | ||
Lecture 8 Thursday 02/06/25 |
Segmentation & Detection I |
Readings: #1: Jonathan Long, Evan Shelhamer, Trevor Darrell #2: Olaf Ronneberger et al. Optional Readings: #3: Sixiao Zheng et al. #4: Enze Xie et al. |
Shubham | ||
Week 5 | |||||
Lecture 9 Tuesday 02/11/25 |
Segmentation & Detection II |
Readings: #1: Pedro F Felzenszwalb et.al. #2: Ross Girshick et.al. #3: Joseph Redmon et al. #4: Nicolas Carion et al. #5: Kaiming He et al. #6: Alexander Kirillov et al. Optional Readings: #7: Bowen Cheng et al. |
Shubham | ||
Lecture 10 Thursday 02/13/25 |
Generative Models I |
Readings: #1: Ian J. Goodfellow et al. #2: Alec Radford, Luke Metz, Soumith Chintala #3: Phillip Isola et al. Optional Readings: #4: Tero Karras, et al. #5: Jun-Yan Zhu*, Taesung Park* et al. |
Shubham | ||
Week 6 | |||||
Lecture 11 Tuesday 02/18/25 |
Generative Models II |
Readings: #1: Diederik P Kingma, Max Welling #2: Aaron van den Oord et al. #3: Patrick Esser et al. Optional Readings: #4: Diederik P. Kingma, Max Welling #5: Aaron van den Oord et al. |
Shubham | ||
Lecture 12 Thursday 02/20/25 |
Generative Models III |
Readings: #1: Jonathan Ho, Ajay Jain, Pieter Abbeel #2: Yang Song et al. Optional Readings: #3: Yang Song, Diederik P. Kingma #4: J Sohl-Dickstein et al. |
Shubham | HW1 Due; HW2 Out (Generative Modeling - GAN, VAE, Diffusion) | |
Week 7 | |||||
Lecture 13 Tuesday 02/25/25 |
SSL I |
Readings: #1: Deepak Pathak et al. #2: Richard Zhang et al. #3: Kaiming He et al. Optional Readings: #4: Jeff Donahue, Karen Simonyan #5: Mark Chen et al. |
Shubham | ||
Lecture 14 Thursday 02/27/25 |
SSL II |
Readings: #1: Ting Chen et al. #2: Kaiming He et al. #3: Aaron van den Oord, Yazhe Li, Oriol Vinyals Optional Readings: #4: Jean-Bastien Grill et al. #5: Xinlei Chen and Kaiming He |
Shubham | ||
Week 8 | |||||
Lecture 15 Tuesday 03/04/25 |
Break | ||||
Lecture 15 Thursday 03/06/25 |
Break | ||||
Week 9 | |||||
Lecture 15 Tuesday 03/11/25 |
Vision & Language I |
Readings: #1: Stanislaw Antol*, Aishwarya Agrawal*, et al. #2: Alec Radford et al. #3: Haotian Liu et al. Optional Readings: #4: Junnan Li et al. |
Jun-Yan Zhu | ||
Lecture 16 Thursday 03/13/25 |
Vision & Language II |
Readings: #1: Elman Mansimov et al. #2: Robin Rombach et al. #3: Aditya Ramesh et al. Optional Readings: #4: Chitwan Saharia et al. #5: Jiahui Yu et al. #6: Kang et al. |
Jun-Yan Zhu | ||
Week 10 | |||||
Lecture 17 Tuesday 03/18/25 |
Learning & 3D I |
Readings: #1: Derek Hoiem, Alexei A. Efros, Martial Hebert #2: David Eigen, Rob Fergus #3: Georgia Gkioxari, Jitendra Malik, Justin Johnson |
Shubham | ||
Lecture 18 Thursday 03/20/25 |
Learning & 3D II |
Readings: #1: Charles R. Qi*, Hao Su* et al. #2: Yue Wang et al. #3: Jeong Joon Park et al. |
Shubham | HW2 Due; HW3 Out (VQA with Transformers) | |
Week 11 | |||||
Lecture 19 Tuesday 03/25/25 |
Action Recognition & Videos I |
Readings: #1: Karen Simonyan, Andrew Zisserman #2: Du Tran et al. #3: Joao Carreira, Andrew Zisserman |
Shubham | ||
Lecture 20 Thursday 03/27/25 |
Action Recognition & Videos II |
Readings: #1: Anurag Arnab et al. #2: Ze Liu et al. #3: Chen Sun et al. Optional Readings: #4: Zhan Tong et al. |
Shubham | ||
Week 12 | |||||
Lecture 21 Tuesday 04/01/25 |
Promptable Vision Models |
Readings: #1: Jake Snell, Kevin Swersky, Richard S. Zemel #2: Eric Tzeng et al. #3: Chelsea Finn et al. #4: Menglin Jia et al. #5: Amir Bar*, Yossi Gandelsman* et al. #6: Hyojin Bahng et al. |
Shubham | ||
Lecture 21 Thursday 04/03/25 |
Carnival | ||||
Week 13 | |||||
Lecture 22 Tuesday 04/08/25 |
Guest Lecture I: Multi-modal Vision Models |
Readings: TBD |
Guest | ||
Lecture 23 Thursday 04/10/25 |
Guest Lecture II: Vision for Robots |
Readings: TBD |
Guest | HW3 Due | |
Week 14 | |||||
Lecture 24 Tuesday 04/15/25 |
Efficient Deep Learning |
Readings: #1: Song Han, Huizi Mao, William J Dally #2: Geoffrey Hinton, Oriol Vinyals, Jeff Dean #3: Andrew G. Howard, et al. Optional Readings: #4: Han Cai et al. #5: Tri Dao et al. #6: Daniel Bolya et al. |
Shubham | ||
Lecture 25 Thursday 04/17/25 |
Conclusion |
No Readings |
Shubham | ||
Week 15 | |||||
Lecture 26 Tuesday 04/22/25 |
Poster Presentation I | ||||
Lecture 27 Thursday 04/24/25 |
Poster Presentation II | ||||
Final Week | |||||
Wednesday 05/07/25 | Grades Released |