Final Project: Open Ended!
Due Tuesday May 8, noon
- Any of the following Kaggle Contests:
- Implement any approach for Intrinsic Image Decomposition (possible dataset: http://www.cs.toronto.edu/~rgrosse/intrinsic/).
- Implement an approach for shadow detection: Try to find cast
shadows in outdoor images. Possible Dataset:
- Creating adversarial examples to fight classification (Description: https://blog.openai.com/adversarial-example-research/).
- Tracking: Try to track players and the ball in a sports video.
Projects will be turned in via web-page. Your webpage should include these sections:
- Names of everyone in your group.
- Introduction (problem –Why, with real‐world
applications), and one illustrative example output.
- Related Work (What has been done, with a few
- Your Approach (How you are going to do it, with
algorithms, equations, figures)
- Your Implementation and Analysis (What you do,
with images, tables, and numbers)
- Your Conclusions (Itemized conclusions, observations