Lecture 1 Part 2
Lecture 1 Part 2
cat
cat
cat
cat
Tasks Models
CAT GRASS, CAT, TREE, DOG, DOG, CAT DOG, DOG, CAT
SKY
No spatial extent No objects, just pixels Multiple Object This image is CC0 public domain
Running? Jumping?
Style Transfer
DALL-E 2
Contrastive pre-training in CLIP. The blue squares are the pairs for which we want to
optimize the similarity. Image derived from https://github.com/openai/CLIP
Zhou et al., 3D Shape Generation and Completion through Point-Voxel Diffusion (2021) Gkioxari et al., “Mesh R-CNN”, ICCV 2019
Li et al., BEHAVIOR-1K: A Benchmark for Embodied AI with 1,000 Everyday Activities and Mandlekar and Xu et al., Learning to Generalize Across Long-
Realistic Simulation (2022) Horizon Tasks from Human Demonstrations (2020)
That’s Fei-Fei
- Lectures will not be streamed on Zoom but will be broadcast live via Panopto
- Slides will be posted on the course website shortly before each lecture
- All lectures will be recorded and uploaded to Canvas after the lecture under the
“Panopto Course Videos” Tab.
Hands-on tutorials, with more practical details than the main lecture
Check Canvas for the Zoom link for the discussion sessions! Recordings will be
available on Canvas.
For questions about assignments, final project, midterm, logistics, etc, use Ed!
Access: Canvas -> Deep Learning for Computer Vision -> Ed Discussion
SCPD students: Use your @stanford.edu address to register for Ed; contact scpd-
[email protected] for help.
- K-Nearest Neighbor
- Linear classifiers: SVM, Softmax
- Two-layer neural network
- Image features
An auto-grading system: