====== Challenge: Personalized Age Estimation ======

**📅 Deadline:** 31.12.2025 21:59

**🏦 Points:** 15 (beating baseline) + 20 (leader-board)

This page outlines the course challenge on [[https://cw.felk.cvut.cz/brute/student/course/BE4M33SSU/challenge1|Personalized Age Estimation]]. This project is intended for students interested in exploring the course topics in greater depth through a practical application.

Participation is optional and **does not contribute to the mandatory homework point total**. However, successful completion provides a more direct and easier path to achieving a final grade of **A** or **B**.

<note warning>**Update 07.10.2025**: A PyTorch checkpoint of the pretrained model is now available at [[https://cmp.felk.cvut.cz/courses/SSU/ssu_challenge_template_checkpoint_version.zip | this link]]. Feel free to finetune the weights. Make sure to follow the rules and use only the provided data from the [[https://cmp.felk.cvut.cz/courses/SSU/ssu_challenge_template.zip | template]]. </note>

===== Task Description =====

The challenge is to implement a model for **personalized age estimation**. The objective is to improve the age prediction for an individual by leveraging a reference image of the same person with a known age.

The prediction problem is defined as follows: Given **face 1** of a person, its corresponding **age 1**, and a second image, **face 2**, of the same person, the task is to predict **age 2**.

For instance, using the first image of Zdeněk Svěrák and his known age, the task is to predict his age in the second image.

{{:courses:be4m33ssu:challenges:158153273_70810f.jpg?direct&400 | Reference Image: Age is known}}
{{ :courses:be4m33ssu:challenges:162667470_7d6846.jpg?direct&400  | Target Image: Predict this age }}

===== Rules =====
  * **You can only use the provided data** 
  * **The solution must finish under 15 minutes on BRUTE** (The baseline runs for ~4 minutes)
  * **You must work independently**. Discussions are encouraged, however, everyone must submit their own unique submission

===== Provided Resources =====

A [[https://cmp.felk.cvut.cz/courses/SSU/ssu_challenge_template.zip | template (.zip)]] is provided, containing the dataset and a baseline solution.

<note tip> Try to submit the baseline solution to see the leader-board

(ZIP the provided files without the dataset)</note>
==== Dataset ====

The dataset is partitioned into `train`, `val`, and `test` sets.
  * You are **only permitted to use the provided data**.
  * You may use the data splits as you see fit (e.g., merge them for training, create a new validation split, etc.).
  * The template code demonstrates the data loading procedure and structure.
  * We evaluate your solutions on a hidden test set, which is roughly the size of the combined public `train`, `val`, and `test` sets.

The age distribution is consistent across the data splits, meaning performance on the public data should generalize to the hidden evaluation set.

{{:courses:be4m33ssu:challenges:age_distributions_2d.png?direct&800| Age Distribution Across Data Splits}}

==== Baseline Model and Solution ====

The template includes a pre-trained **ResNet-50 model**.
  * It is provided as a **JIT scripted** module for efficient inference.
  * The model outputs **age posteriors** (a probability distribution over different ages), which may be a useful feature for your solution.
  * For students who wish to fine-tune the model, a **weight checkpoint** is available upon request. Please contact us if you require it.

The baseline script implements a simple offset-based approach:
<code>
# Calculate the prediction error on the reference image
offset = true_age_1 - prediction(face1)

# Adjust the target prediction using half of the calculated error
final_prediction_face_2 = prediction(face2) + (offset / 2)
</code>

The objective of the challenge is to design and implement a method that improves upon this baseline.

===== Grading and Evaluation =====

Solutions will be evaluated based on **Mean Absolute Error (MAE)** on a hidden test set.
  * **15 points** are awarded for achieving **MAE of 4.5 or better**. The provided baseline achieves MAE of ~4.85.
  * **Up to 20 additional points** will be awarded to the top-performing solutions on the leaderboard.
  * To be eligible for any points from the challenge, participants must submit a very short PDF that briefly explains their approach (a single paragraph is enough) along with the training code. This requirement is in place to ensure that no additional data was used during training and so that we can learn something from your solutions.

<note> The exact point distribution for the top solutions will be determined based on the final standings. We will likely interpolate between the top contender and the baseline to assign the points. </note>

You can see the leader-board after submitting a solution and clicking the **AE Result** button.

{{:courses:be4m33ssu:challenges:leaderboard.png?direct&400|}}
{{:courses:be4m33ssu:challenges:leaderboard2.png?direct&400|}}

===== Submission and Testing Procedures =====

==== Local Testing ====
After implementing your solution, you can test it locally using the provided public test cases:

  python main.py test-cases/public/instances/test_processed.json

==== Submission ====
  * Submit your completed code as a single **.zip** file via the [[https://cw.felk.cvut.cz/brute/student/course/BE4M33SSU/challenge1|BRUTE]] system.
  * The evaluation will be performed automatically.

<note important> Ensure that all Python files are located in the root of the submitted .zip archive. </note>

<note important> Submissions are evaluated sequentially (BRUTE processes GPU jobs one submission at a time). Because of this system limitation, results for simultaneous submissions may be delayed. To avoid long queues and reduce wait times for everyone, please do not spam the submission system with incremental changes. Instead, refine and test locally, and submit to BRUTE sparingly — for example, no more than once per day.</note>

===== Environment =====

The evaluation is performed using Python in a Docker environment with GPU support: [[https://hub.docker.com/r/brute/brute_pytorch_gpu|BRUTE PyTorch GPU Docker]].
===== Support and Contact =====

For any questions or issues, please contact **Jakub Paplhám** at <paplhjak@fel.cvut.cz>. He is also available in person during the 2nd and 3rd seminars every Thursday or at the lectures.