Date | Description | Course Materials | Events | Deadlines |
---|---|---|---|---|
04/01 |
Lecture 1: Introduction Computer vision overview Course overview Course logistics [slides 2] |
|||
——— | Deep Learning Basics | |||
04/03 |
Lecture 2: Image Classification with Linear Classifiers The data-driven approach K-nearest neighbor Linear Classifiers Algebraic / Visual / Geometric viewpoints Softmax loss |
|||
04/04 |
Python / Numpy Review Session
| 12:30-1:20pm PT | ||
04/08 |
Lecture 3: Regularization and Optimization Regularization Stochastic Gradient Descent Momentum, AdaGrad, Adam Learning rate schedules |
|||
04/09 | Assignment 1 out | |||
04/10 |
Lecture 4: Neural Networks and Backpropagation Multi-layer Perceptron Backpropagation |
|||
04/11 |
Backprop Review Session
| 12:30-1:20pm PT | ||
——— | Perceiving and Understanding the Visual World | |||
04/15 |
Lecture 5: Image Classification with CNNs History Higher-level representations, image features Convolution and pooling |
|||
04/17 |
Lecture 6: CNN Architectures Batch Normalization Transfer learning AlexNet, VGG, ResNet |
|||
04/18 |
Final Project Overview and Guidelines
| 12:30-1:20pm PT | ||
04/22 |
Lecture 7: Recurrent Neural Networks RNN, LSTM, GRU Language modeling Image captioning Sequence-to-sequence |
|||
04/23 | Assignment 2 out | Assignment 1 due | ||
04/24 |
Lecture 8: Attention and Transformers Self-Attention Transformers |
|||
04/25 |
PyTorch Review Session
| 12:30-1:20pm PT | Project proposal due | |
04/29 |
Lecture 9: Object Detection, Image Segmentation, Visualizing and Understanding Single-stage detectors Two-stage detectors Semantic/Instance/Panoptic segmentation Feature visualization and inversion Adversarial examples DeepDream and style transfer |
|||
05/01 |
Lecture 10: Video Understanding Video classification 3D CNNs Two-stream networks Multimodal video understanding |
|||
05/02 |
RNNs & Transformers
| 12:30-1:20pm PT | ||
05/06 |
Lecture 11: Large Scale Distributed Training |
|||
05/07 | Assignment 2 due | |||
——— | Generative and Interactive Visual Intelligence | |||
05/08 |
Lecture 12: Self-supervised Learning Pretext tasks Contrastive learning Multisensory supervision |
|||
05/09 |
Midterm Review Session
| 12:30-1:20pm PT | ||
05/13 |
In-Class Midterm |
12:00-1:20pm PT | ||
05/14 | Assignment 3 out | |||
05/15 |
Lecture 13: Generative Models 1 Variational Autoencoders Generative Adversarial Network Autoregressive Models |
|||
05/16 | Project milestone due | |||
05/20 |
Lecture 14: Generative Models 2 Diffusion models |
|||
05/22 |
Lecture 15: Vision and Language |
|||
05/27 |
Lecture 16: 3D Vision 3D shape representations Shape reconstruction Neural implicit representations |
|||
05/28 | Assignment 3 due | |||
05/29 |
Lecture 17: Robot Learning Deep Reinforcement Learning Model Learning Robotic Manipulation |
|||
06/03 |
Lecture 18: Human-Centered AI |
|||
06/04 | Project report due | |||
06/11 (Tentative) |
Final Project Poster Session |