🌍 IOAI 2024, Scientific Round, On-Site

The Madarian Cow Mystery

Modify text embeddings and latents of a diffusion model so that prompts mentioning a cow also produce a fire hydrant, checked by an object detector.

Statement: English · Original statement ↗
Data: Hugging Face dataset: InternationalOlympiadAI/CV_problem_onsite ↗ · Hugging Face dataset: InternationalOlympiadAI/CV_problem_test ↗ · Hugging Face dataset: InternationalOlympiadAI/CV_onsite_labels ↗ · Training data ↗ · Test data ↗
To hand in: A predictions file and the notebook that makes it
Hardware: Needs a GPU (free Colab works)
Data size: 324.8 MB
Data type: 🖼️ Images
Estimated difficulty: ★★★★☆
Solution: See a solution · best opened after you have tried

Get ready on the platform

The chapters of the learning path that prepare for this problem.

These chapters are picked from the solution: showing them may hint at the approach.

›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.

The statement, data and solutions belong to their authors; we only link to them. Licence : CC-BY-4.0.