← All problems
Illustration by IOAI Training
🇧🇬 Bulgaria NCAI 2026, National Competition in AI, final (in-person) round
Training-Free Statistical Defect Localisation in Latent Space
✍️ Solved by us
Without any training, flag and localise product defects from precomputed patch embeddings while staying robust to a distribution shift between two regimes.
- Statement
- Bulgarian · Read it in English (Google Translate)
- To hand in
- A Python function
- Data type
- 🖼️ Images
- Estimated difficulty
- ★★★★☆
- Correction
- Our worked correction · 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.
Unofficial copy: the organisers' original may differ.
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