Date | Description | Course Materials | Events | Deadlines |
---|---|---|---|---|
04/02 |
Lecture 1: Introduction Computer vision overview Course overview Course logistics [slides 1] [slides 2] |
|||
——— | Deep Learning Basics | |||
04/04 |
Lecture 2: Image Classification with Linear Classifiers The data-driven approach K-nearest neighbor Linear Classifiers Algebraic / Visual / Geometric viewpoints SVM and Softmax loss [slides] |
Image Classification Problem Linear Classification |
||
04/05 |
Python / Numpy Review Session
[Colab] [Tutorial] | 12:30-1:20pm PT |
Assignment 1 out
|
|
04/09 |
Lecture 3: Regularization and Optimization Regularization Stochastic Gradient Descent Momentum, AdaGrad, Adam Learning rate schedules [slides] |
Optimization |
||
04/11 |
Lecture 4: Neural Networks and Backpropagation Multi-layer Perceptron Backpropagation [slides] |
Backprop Linear backprop example Suggested Readings:
|
||
04/12 |
Backprop Review Session
[Colab] | 12:30-1:20pm PT | ||
——— | Perceiving and Understanding the Visual World | |||
04/16 |
Lecture 5: Image Classification with CNNs History Higher-level representations, image features Convolution and pooling [slides] |
Convolutional Networks |
||
04/18 |
Lecture 6: CNN Architectures Batch Normalization Transfer learning AlexNet, VGG, GoogLeNet, ResNet [slides 1] [slides 2] [review] |
AlexNet, VGGNet, GoogLeNet, ResNet | ||
04/19 |
Final Project Overview and Guidelines
| 12:30-1:20pm PT |
Assignment 2 out |
Assignment 1 due |
04/22 | Project proposal due | |||
04/23 |
Lecture 7: Recurrent Neural Networks RNN, LSTM, GRU Language modeling Image captioning Sequence-to-sequence |
Suggested Readings: | ||
04/25 |
Lecture 8: Attention and Transformers Self-Attention Transformers |
Suggested Readings:
|
||
04/26 |
PyTorch Review Session
[Colab] | 12:30-1:20pm PT | ||
04/30 |
Lecture 9: Object Detection and Image Segmentation Single-stage detectors Two-stage detectors Semantic/Instance/Panoptic segmentation |
FCN, R-CNN, Fast R-CNN, Faster R-CNN, YOLO | ||
05/02 |
Lecture 10: Video Understanding Video classification 3D CNNs Two-stream networks Multimodal video understanding |
|||
05/03 |
Midterm Review Session
| 12:30-1:20pm PT | ||
05/06 | Assignment 2 due | |||
05/07 |
Lecture 11: Visualizing and Understanding Feature visualization and inversion Adversarial examples DeepDream and style transfer |
|||
05/09 |
In-Class Midterm |
12:00-1:20pm | ||
05/10 |
RNNs & Transformers
[Colab] | 12:30-1:20pm PT | ||
05/11 | Project milestone due | |||
——— | Generative and Interactive Visual Intelligence | |||
05/14 |
Lecture 12: Self-supervised Learning Pretext tasks Contrastive learning Multisensory supervision |
Suggested Readings:
|
Assignment 3 out | |
05/16 |
Lecture 13: Generative Models Generative Adversarial Network Diffusion models Autoregressive models |
|||
05/21 |
Lecture 14: Guest Lecture on Vision Language Models by OpenAI SORA Team |
|||
05/23 |
Lecture 15: Robot Learning Deep Reinforcement Learning Model Learning Robotic Manipulation |
|||
05/28 |
Lecture 16: 3D Vision 3D shape representations Shape reconstruction Neural implicit representations |
Assignment 3 due | ||
——— | Human-Centered Applications and Implications | |||
05/30 |
Lecture 17: Human-Centered Artificial Intelligence |
|||
06/04 |
Lecture 18: Guest Lecture: TBD |
|||
06/05 | Project final report due | |||
06/12 |
Final Project Poster Session |