Model that acheived 5th place overall on FathomNet 2025 kaggle competition (competition link: https://www.kaggle.com/competitions/fathomnet-2025/overview)

Associated code: https://github.com/robertahunt/FathomNet2025

Things I think worked well:

  1. Choosing the class which minimized the expected loss based on the distance matrix (and not the class with the highest probability) and implementing this as a matrix multiplication with the distance matrix.
  2. Implementing a small Graph Neural Network layer - the idea here was to help in cases where there are many specimens of the same species in a single overall image, and one is easy to classify, but the other instances may be blurry. Then adding a graph layer could help guide the model to the correct classification.
  3. Using EfficientNet as a simple and fast base network, made experimenting fairly fast and simple.

Things I wish I had done differently:

  1. Setting the seed earlier: I initially used a random seed each time, which made measuring progress and reproducing results difficult. It wasn't until near the end I changed this. This is why the results using this seed also sadly do not match perfectly with the public results.
  2. Making the saving and logging process cleaner overall so it would be easier to compare results
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support