ECE59500CV
Deep Learning for Computer Vision
Fall 2020
General Information
Lectures: M,W,F 3:30pm - 4:20pm, online synchronous via
zoom, meeting ID: 928 5663 6867, passcode: ECE59500CV.
Instructor:
Jeffrey Mark Siskind,
EE313e, 765/496-3197,
qobi@purdue.edu
Office Hours: T 5:00pm - 6:00pm, online synchronous via
zoom, meeting ID: 928 5663 6867, passcode: ECE59500CV.
ece59500cv-students-list@ecn.purdue.edu
ece59500cv-staff-list@ecn.purdue.edu
Syllabus
Brightspace
BibTeX file for papers we will cover in this course
github repository
deep learning
segmentation
object classification and localization
activity classification and localization
semantic segmentation
depth reconstruction
3D reconstruction
generative adversarial networks
image and video captioning
image and video retrieval
- Lecture 1: Course Overview
Monday 24 August 2020
- Lecture 2: Functions
A.G. Baydin,
B.A. Pearlmutter,
A.A. Radul, and
J.M. Siskind,
`Automatic differentiation in machine learning: a survey,'
Journal of Machine Learning Research (JMLR),
18(153):1-43,
2018.
Wednesday 26 August 2020
code_w26aug2020a.py
code_w26aug2020b.py
- Lecture 3: Automatic Differentiation-I
Friday 28 August 2020
Whiteboard
tracing.py
- Lecture 4: Automatic Differentiation-II
Monday 31 August 2020
Whiteboard
code_m31aug2020.py
forward_mode.py
- Lecture 5: Neural Networks
Wednesday 2 September 2020
code_w2sep2020.py
gui.py
linear_classifier.py
linear_classifier_gui.py
two_layer_perceptron.py
two_layer_perceptron_gui.py
- Lecture 6: Automatic Differentiation-III
Friday 4 September 2020
Whiteboard
code_f4sep2020.txt
- Lecture 7: Backpropagation and Reverse-Mode AD
B.A. Pearlmutter and
J.M. Siskind,
`Reverse-Mode AD in a functional framework:
Lambda the Ultimate Backpropagator,'
ACM Transactions on Programming Languages and Systems (TOPLAS),
30(2):1-36,
2008.
Monday 7 September 2020
Whiteboard
code_m7sep2020.txt
code_m7sep2020.bib
code_m7sep2020.tex
reverse_mode.py
linear_classifier_pytorch_gui.py
two_layer_perceptron_pytorch_gui.py
- Lecture 8: Nestable AD
J.M. Siskind and
B.A. Pearlmutter,
`Nesting forward-mode AD in a functional framework,'
Higher-Order and Symbolic Computation (HOSC),
21(4):361-376,
2008.
Wednesday 9 September 2020
Whiteboard
code_w9sep2020.py
nestable_forward_mode.py
nestable_reverse_mode.py
equilibrium.py
- Lecture 9: Model-Based Vision
D.G. Lowe,
`Three-dimensional object recognition from single two-dimensional images,'
Artificial Intelligence (AIJ),
31(3):355-395,
1987.
D.F. Dementhon and
L.S. Davis,
`Model-based object pose in 25 lines of code,'
International Journal of Computer Vision (IJCV),
15(1-2):123-141,
1995.
Friday 11 September 2020
Whiteboard
code_f11sep2020.py
model_based_vision_gui.py
model_based_vision.py
- Lecture 10: Histograms of Oriented Gradients
N. Dalal and
B. Triggs,
`Histograms of oriented gradients for human detection,'
Computer Vision and Pattern Recognition (CVPR),
pp. 886-893,
2005.
Monday 14 September 2020
Whiteboard
- Lecture 11: Deformable Part Models
P.F. Felzenszwalb,
R.B. Girshick,
D. McAllester, and
D Ramanan,
`Object detection with discriminatively trained part-based models,'
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),
32(9):1627-1645,
2010.
Wednesday 16 September 2020
- Lecture 12: AlexNet
A. Krizhevsky,
I. Sutskever, and
G.E. Hinton,
`ImageNet classification with deep convolutional neural networks,'
Advances in Neural Information Processing Systems (NeurIPS),
pages 1097-1105,
2012.
Friday 18 September 2020
Whiteboard
- Lecture 13: VGG-16
K. Simonyan and
A. Zisserman,
`Very deep convolutional networks for large-scale image recognition,'
International Conference on Learning Representations (ICLR),
2015.
Monday 21 September 2020
Whiteboard
- Lecture 14: Inception v1
C. Szegedy,
W. Liu,
Y. Jia,
P. Sermanet,
S. Reed,
D. Anguelov,
D. Erhan,
V. Vanhoucke, and
A. Rabinovich,
`Going deeper with convolutions,'
Computer Vision and Pattern Recognition (CVPR),
2015.
Wednesday 23 September 2020
Whiteboard
- Lecture 15: Batch Normalization
S. Ioffe and
C. Szegedy,
`Batch normalization: accelerating deep network training by reducing internal
covariate shift,'
International Conference on Machine Learning (ICML),
pp. 448-456,
2015.
Friday 25 September 2020
Whiteboard
- Lecture 16: ResNet
K. He,
X. Zhang,
S. Ren, and
J. Sun,
`Deep residual learning for image recognition,'
Computer Vision and Pattern Recognition (CVPR),
pp. 770-778,
2016.
Monday 28 September 2020
Whiteboard
- Lecture 17: Inception v3
C. Szegedy,
V. Vanhoucke,
S. Ioffe,
J. Shlens, and
Z. Wojna,
`Rethinking the Inception architecture for computer vision,'
Computer Vision and Pattern Recognition (CVPR),
pp. 2818-2826,
2016.
Wednesday 30 September 2020
Whiteboard
- Lecture 18: Inception v4
C. Szegedy,
S. Ioffe, and
V. Vanhoucke,
`Inception-v4, Inception-ResNet and the impact of residual connections on
learning,'
Conference on Artificial Intelligence (AAAI),
2017.
Friday 2 October 2020
- Lecture 19: DenseNet
G. Huang,
Z. Liu,
L. Van Der Maaten, and
K.Q. Weinberger,
`Densely connected convolutional networks,'
Computer Vision and Pattern Recognition (CVPR),
pp. 4700-4708,
2017.
Monday 5 October 2020
Whiteboard
- Lecture 20: R-CNN
R. Girshick,
J. Donahue,
T. Darrell, and
J. Malik,
`Rich feature hierarchies for accurate object detection and semantic
segmentation,'
Computer Vision and Pattern Recognition (CVPR),
pp. 580-587,
2014.
Wednesday 7 October 2020
- Lecture 21: Fast R-CNN
R. Girshick,
`Fast R-CNN,'
Computer Vision and Pattern Recognition (CVPR),
pp. 1440-1448,
2015.
Friday 9 October 2020
Whiteboard
- Lecture 22: Faster R-CNN
S. Ren,
K. He,
R. Girshick, and
J. Sun,
`Faster R-CNN: Towards real-time object detection with region proposal
networks,'
Advances in Neural Information Processing Systems (NeurIPS),
pp. 91-99,
2015.
Monday 12 October 2020
- Lecture 23: YOLO
J. Redmon,
S. Divvala,
R. Girshick, and
A. Farhadi,
`You only look once: Unified, real-time object detection,'
Computer Vision and Pattern Recognition (CVPR),
pp. 779-788,
2016.
Wednesday 14 October 2020
- Lecture 24: Class Canceled
Friday 16 October 2020
- Lecture 25: SSD
W. Liu,
D. Anguelov,
D. Erhan,
C. Szegedy,
S. Reed,
C.-Y. Fu, and
A.C. Berg,
`SSD: Single shot multibox detector,'
European Conference on Computer Vision (ECCV),
pp. 21-37,
2016.
Monday 19 October 2020
Whiteboard
- Lecture 26: Mask R-CNN
K. He,
G. Gkioxari,
P. Dollar, and
R. Girshick,
`Mask R-CNN,'
International Conference on Computer Vision (ICCV),
pp. 2961-2969,
2017.
Wedneday 21 October 2020
- Lecture 27: FPN
T.-Y. Lin,
P. Dollar,
R. Girshick,
K. He,
B. Hariharan, and
S. Belongie,
`Feature pyramid networks for object detection,'
Computer Vision and Pattern Recognition (CVPR),
pp. 2117-2125,
2017.
Friday 23 October 2020
Whiteboard
- Lecture 28: YOLO v2
J. Redmon and
A. Farhadi,
`YOLO9000: better, faster, stronger,'
Computer Vision and Pattern Recognition (CVPR),
pp. 7263-7271,
2017.
Monday 26 October 2020
- Lecture 29: DeepVideo
A. Karpathy,
G. Toderici,
S. Shetty,
T. Leung,
R. Sukthankar, and
L. Fei-Fei,
`Large-scale video classification with convolutional neural networks,'
Computer Vision and Pattern Recognition (CVPR),
pp. 1725-1732,
2014.
Wednesday 28 October 2020
Whiteboard
- Lecture 30: Two-Stream Networks
K. Simonyan and
A. Zisserman,
`Two-stream convolutional networks for action recognition in videos,'
Advances in Neural Information Processing Systems (NeurIPS),
pp. 568-576,
2014.
Friday 30 October 2020
Whiteboard
- Lecture 31: TDD
L. Wang,
Y. Qiao, and
X. Tang,
`Action recognition with trajectory-pooled deep-convolutional descriptors,'
Computer Vision and Pattern Recognition (CVPR),
pp. 4305-4314,
2015.
Monday 2 November 2020
Whiteboard
- Lecture 32: Reading Day
Wednesday 4 November 2020
- Lecture 33: C3D
D. Tran,
L. Bourdev,
R. Fergus,
L. Torresani, and
M Paluri,
`Learning spatiotemporal features with 3D convolutional networks,'
International Conference on Computer Vision (ICCV),
pp. 4489-4487,
2015.
Friday 6 November 2020
- Lecture 34: Beyond Short Snippets
J. Yue-Hei Ng,
M. Hausknecht,
S. Vijayanarasimhan,
O. Vinyals,
R. Monga, and
G. Toderici,
`Beyond short snippets: Deep networks for video classification,'
Computer Vision and Pattern Recognition (CVPR),
pp. 4694-4702,
2015.
Monday 9 November 2020
Whiteboard
- Lecture 35: Fusion
C. Feichtenhofer,
A. Pinz, and
A. Zisserman,
`Convolutional two-stream network fusion for video action recognition,'
Computer Vision and Pattern Recognition (CVPR),
pp. 1933-1941,
2016.
Wednesday 11 November 2020
Whiteboard
- Lecture 36: Class Canceled
Friday 13 November 2020
- Lecture 37: Class Canceled
Monday 16 November 2020
- Lecture 38: Student Presentations
Wednesday 18 November 2020
- Lecture 39: Student Presentations
Friday 20 November 2020
- Lecture 40: Student Presentations
Monday 23 November 2020
- Lecture 41: Student Presentations
Monday 30 November 2020
- Lecture 42: Student Presentations
Wednesday 2 December 2020
- Lecture 43: Student Presentations
Friday 4 December 2020
ECE59500CV | ECE | ECN | Purdue University