In this competition, you'll develop an AI-based ranking system that ranks the samples based on their **levels of label noise**. Observe that:
1. **the main idea of this competition is to rank the images automatically, and NOT to re-annotate the dataset,**
2. **the ranking should be created using the level of *label noise*, and not the level of image noise.**

To this end, you'll be given a semantic segmentation dataset composed of 5,000 256x256 images and their corresponding (*noisy*) labels. The labels consist of two classes: background (encoded as 0 in the label data) and building (encoded as 1 in the label data).

Success is measured by comparing the submitted ranking with an undisclosed one and calculating the [Kendall Tau score](https://en.wikipedia.org/wiki/Kendall_rank_correlation_coefficient).

Finally, this challenge is part of the [MVEO workshop](https://mveo.github.io/challenge.html) in conjunction with [BMVC 2024](https://bmvc2024.org/).