← All problems
🇬🇪 Georgia AI Olympiad 2025, Final Round
Image Classification with Weak Labels
Build weak labels from machine-generated captions and train an eight-class image classifier from scratch.
- Statement
- Georgian · Read it in English (Google Translate)
- Data
- The data comes with the statement.
- To hand in
- A predictions file and the notebook that makes it
- Data type
- 🖼️ Images
- Estimated difficulty
- Unknown
Get ready on the platform
The foundations of the learning path for this kind of data.
›How to tackle it
- Read the statement. What to hand in, the metric that scores you, the time and hardware limits.
- Explore the data. Size, format, missing values, how the labels are spread.
- Score yourself first. Keep part of the training data aside to measure your work before submitting.
- Start simple, then improve. A first solution that works end to end, then one change at a time.
- Compare with a solution. Once you have searched, open it and see what you would have done differently.
Links taken from community indexes (checklist.sota-ai.org, awesome-ioai-tasks) and not all checked.
The statement, data and solutions belong to their authors; we only link to them.
Are you the author or organiser? Ask for a correction or removal