| Date | Content | Reading | |
| Sept 8 (week 1) | UBC Welcome day, no class | ||
| Sept 10 | Introduction lecture slides The first lecture will be on zoom, access via Canvas or mail me for the link. - Challenges in using deep learning for creative tasks - Course expectations and grading - First steps in PyTorch Homework 1 release assignment1_V2.zip |
SIGGRAPH program / trailer Pytorch intro | |
| Sep 15 (week 2) | Deep learning basics and best practices lecture slides - regression/classification, objective functions - stochastic gradient descent, vanishing and exploding gradients. Extra: How to read a paper efficiently? |
Deep Learning Book - Chapter 8 Adam Optimizer |
|
| Sep 17 | Network architectures for image processing
lecture slides - Which neural network architectures work, why and how? - Differentiation and optimization - ResNet, DenseNet, UNet, FlowNet, MaskRCNN Extra: How to give a good presentation? |
Deep Learning Book - Chapter 9 ResNet, Unet | |
| Sep 22 (week 3) | Advanced architectures and representing sparse 2D keypoints lecture slides How to give a good talk? - heat maps, part-affinity fields - regression vs. classification Homework 1 due. Homework 2 release |
Heat Maps Part Affinity Fields |
|
| Sep 24 |
Representing sparse 2D keypoints lecture slides Presentations: Objective functions and log-likelihood Christopher Bishop, Mixture Density Networks paper Submit review on the day before every presentation day. |
Read the papers listed for each presentation session. |
|
| Sep 29 (week 4) | Representing 3D skeletons and point clouds
lecture slides
- PointNet, articulated skeletons - Chamfer distance and other metrics (MPJPE, PCK) - Affine and perspective transformations |
PointNet |
|
| Oct 1 |
Presentations: TBD Homework 2 due. Homework 3 release |
Read the papers listed for each presentation session. |
|
| Oct 6 (week 5) | GANs and unpaired image translation
lecture slides - cycle consistency - style transfer |
Cycle Gan Style transfer |
|
| Oct 8 | Presentations: TBD | ||
| Oct 13 (week 6) | Representing and learning shapes
lecture slides - voxels, implicit functions, location maps - uv-coordinates, graph CNN, spiral convolution Homework 3 due. |
Dense Pose Location Maps Spiral convolution |
|
| Oct 15 |
Presentations: TBD |
||
| Oct 19 | Submit project pitch video (3min, .mp4) or slides (PDF, three slides incl. title) | ||
| Oct 20 (week 7) |
Project Pitches(3 min pitch) |
||
| Oct 22 |
Presentations: TBD
how to write a report |
||
| Oct 27 (week 8) | Attention models
- spatial transformers, RoI pooling, attention maps - camera models and multi-view Extra: How to write a paper for the right audience? Report Abstract due. |
RoI pooling,
Spatial Transformer Multi-view Geometry |
Oct 29 | Presentations: TBD |
| Nov 3 (week 9) | Representation learning
lecture slides - auto-encoder (AE) - variational auto-encoder (VAE) Report Related Work section due. |
PCA face model Deep Learning Book - Chapter 14 |
|
| Nov 5 | Presentations: TBD | ||
| Nov 10 (week 10) |
Presentations: TBD Report Method section (up to problem def.) due. |
||
| Nov 12 | Presentations: TBD | ||
| Nov 17 (week 11) |
Presentations: TBD Report Evaluation section (up to datasets and metrics) due. |
||
| Nov 19 | Presentations: TBD | ||
| Nov 24 (week 12) |
Presentations: TBD Report Introduction section due. |
||
| Nov 26 | Presentations: TBD | ||
| Dec 1 (week 13) | Project Presentations. (10 min talk per group, first half of groups) |
||
| Dec 3 | Project Presentations. (10 min talk per group, second half of groups) |
||
| Dec 14 (no class) | Final Project Report submission. (6 page PDF document, 11:59 pm) |
||