Learning CV

Projects and resources for ramping up on computer vision

Classification

References

http://vision.stanford.edu/teaching/cs231b_spring1415/slides/alexnet_tugce_kyunghee.pdf

Projects

Train a binary classifier to distinguish between images of shoes you like and shoes you don't like. (Warning: this will require you to find many pictures of shoes.)

Train a digit classifier on the MNIST database (publically available online.)

Segmentation

References

https://research.googleblog.com/2014/11/a-picture-is-worth-thousand-coherent.html

Projects

Train a network that can distinguish between floors and walls in synthetic data.

Generation

References

Projects

Recreate deep dream: https://www.youtube.com/watch?v=MrBzgvUNr4w&list=PL2-dafEMk2A7EEME489DsI468AB0wQsMV&index=8 (this youtube series is useful.)

Recognition

References

Furniture recognition: https://arxiv.org/pdf/1603.08637.pdf Face Recognition: https://medium.com/@ageitgey/machine-learning-is-fun-part-4-modern-face-recognition-with-deep-learning-c3cffc121d78

Projects

https://cmusatyalab.github.io/openface/ - train to recognize your family's faces

SLAM

References

ORB-SLAM. One of the best algorithms out there. http://webdiis.unizar.es/~raulmur/orbslam/

Projects

This is tricky - SLAM is usually a large compilation of algorithms. Get one of the following parts to work:

Optical flow

Feature matching between frames

Get orb-slam running with a webcam. See if you can make it better.

Reconstructon

References

https://grail.cs.washington.edu/rome/

Projects

Try to implement your favorite paper

Blogs

www.computervisionblog.com/

https://medium.com/@karpathy

Courses

https://www.coursera.org/learn/neural-networks

Textbooks (DONT JUST READ A TEXTBOOK)

Lots of links to different books