...
The main goal is to build a synthetic data creation tool that can take the glyph of a legend label and create a pattern of it that can be used with background templates to create a synthetic training set. The secondary goal will be to measure the performance of various types of models on this problem and try and create a better performing custom model.
Milestone | Quality Metric | Date |
---|---|---|
Show that a synthetic training set can be used to train the base model that is equal to or better then the original training set. | F-score of model trained on synthetic data is >= |
the F-score from training on the original dataset | 3-4 weeks after start | |
Show proof that the initial concept holds weight. The scores from the competition were mostly in the <10% range, with the highest being above 30%. | F-score is >50% | 2 months after start |
F-score is >95% | Project Conclusion |
Project Products
- Research paper describing the tool creating synthetic data
- Research paper contrasting the performance of various models on this problem and my custom one.
- Tool to create synthetic data
- ML Model to train against these glyphs.
- Small talks on research.
...