# Data-Centric Land Cover Classification Challenge — Data

来源：https://www.kaggle.com/competitions/data-centric-land-cover-classification-challenge-2/data

采集时间：2026-10-19T08:31:03Z

## What should I expect the data format to be?

The dataset consists of 5,000 images, each with 256x256 pixels, associated with their noisy labels. The images and labels are PNGs. The labels consist of two classes: background (encoded as 0 in the label data) and building (encoded as 1 in the label data).

## What am I doing?

In this challenge, you will rank samples based on their levels of label noise. In other words, you'll develop an algorithm that assigns a score to each of the 5,000 training samples based on their level of label noise. This score should then be used to rank the data from least to most noisy.

## Files

Although images and labels are in different folders (explained below), the image and corresponding label have the same name. For example, image `training_patches/0_9_2_418_209.png` has a label with exactly the same name, but in the `training_noisy_labels` folder.

    training_patches/ - image files
    training_noisy_labels/ - image noisy labels