Deep Learning for Visual Computing

Link to the lab part of the course (projects): [github]

Course Content

(29.08)
Lecture 1
Syllabus: [Slides]
Introduction: [Slides] - [youtube] 43 min
Review Linear Algebra: [Slides] - [youtube] 1:17 min

(01.09)
Lecture 2
Image Classification Problem: [Slides] - [youtube] 28 min
Data Structures: [Slides] - [youtube] 25 min
Fully Connected Neural Networks: [Slides] - [youtube] 58 min
Notebook - Fully Connected and Convolutional Layers: [colab]
Demo - Experimenting with Tensorflow: [youtube] 10 min
Loss Functions: [Slides] - [youtube] 47 min

(05.09)
Lecture 3
Convolution: [Slides] - [youtube] 1:12 min
Activation Functions: [Slides] - [youtube] 54 min
Network Normalization: [Slides] - [youtube] 56 min

(08.09)
Lecture 4
Backpropagation: [Slides] - [youtube] Part 1: 51 min - [youtube] Part 2: 1:04 min - [youtube] Part 3: 33 min

(12.09)
Lecture 5
Data Normalization: [Slides] - [youtube] 25 min
Network Initialization: [Slides] - [youtube] 51 min
Network Regularization: [Slides] - [youtube] 40 min
Notebook - Dropout: [colab]

(15.09)
Lecture 6
Data Augmentation: [Slides] - [youtube] 44:05 min
Notebook - Data Augmentation: [colab]
Optimization: [Slides] - [youtube] Part 1: 17:49 min - [youtube] Part 2: 1:14:19 min - [youtube] Part 3: 43:22 min

(19.09)
Lecture 7
Classification Architectures: [Slides] - [youtube] Part 1 1:07 min - [youtube] Part 2 1:45 min
Notebook - Print Classification Architecture: [colab]

(22.09)
No teaching

(26.09)
Lecture 8
Training Neural Networks (Justin Johnson): [Slides] - [youtube] 1:19 min
Texture Synthesis: [Slides] - [youtube] 50 min

(29.09)
Lecture 9
Style Transfer: [Slides] - [youtube] 1:14 min

(03.10)
Lecture 10
Visualization: [Slides] - [youtube] 1:04 min
3D Network Visualization (Denis Dmitriev): [youtube] 2 min
Deep Visualization Toolbox (Yason Yosinski): [youtube] 3 min
Network Analysis: [Slides] - [youtube] Part 1 19 min - [youtube] Part 2 16 min - [youtube] Part 3 27 min


(06.10)
Lecture 11
Attention (Justin Johnson): [Slides] - [youtube] 1:11 min

(10.10)
Lecture 12
Object Detection (Justin Johnson): [Slides]
Object Detectors (Justin Johnson): [Slides]
Image Segmentation (Justin Johnson): [Slides]
Object Detection (Justin Johnson 2019): [youtube] 1:21 min
Object Detection and Segmentation (Justin Johnson 2019): [youtube] 1:10 min

(13.10)
Lecture 13
GANs: [Slides] -
[youtube] Part 1 20 min
[youtube] Part 2 24 min
[youtube] Part 3 24 min
[youtube] Part 4 33 min
[youtube] Part 5 43 min

Lecture Free (17.10)

(20.10)
Lecture 14
BERT (Shusen Wang): [youtube] 15 min
Vision Transformer (Shusen Wang): [youtube] 14 min
DETR (Yannic Kilcher): [youtube]
Vision Transformer (Justin Johnson): [Slides]

(24.10)
Lecture 15
Point Clouds: [Slides] -
[youtube] Part 1 17 min
[youtube] Part 2 27 min
[youtube] Part 3 50 min
[youtube] Part 3 21 min

(27.10)
Lecture 17
Neural Architecture Search: [Slides] - [youtube] 37 min
Information Theory Review: [Slides]

(31.10)
Lecture 18
Recurrent Neural Networks / LSTM (Justin Johnson): [Slides]
Recurrent Neural Networks / LSTM (Justin Johnson): [youtube] 1:13 min

(3.11)
Lecture 19
Videos (Justin Johnson): [Slides]
https://web.eecs.umich.edu/~justincj/slides/eecs498/WI2022/598_WI2022_lecture24.pdf
(7.11)
Lecture 20
Self-Supervised Learning (Justin Johnson): [Slides]

(10.11)
Lecture 21
3D Vision (Justin Johnson): [Slides]

(14.11)
Lecture 22
XXX: [Slides]

(17.11)
Lecture 23
XXX: [Slides]

(21.11)
Lecture 24
XXX: [Slides]

(24.11)
Lecture 25
XXX: [Slides]

(28.11)
Lecture 26
XXX: [Slides]

(1.12)
Lecture 27
XXX: [Slides]

(5.12)
Lecture 28
XXX: [Slides]

(8.12)
Lecture 29
XXX: [Slides]