Digital Africa Plantation Counting Challenge
Can you create a semi-supervised algorithm to count trees in plantations in Côte d'Ivoire?
$10 000 USD
20 days to go
153 active · 461 enrolled
Côte dIvoire
Computer Vision
Object Detection
Why RMSE with such high label noise?
Data · 10 Mar 2023, 23:54 · 5

Mean Absolute Error would suite the counting goal better.

Some of the training images are clearly mislabeled (35 vs 0 trees) If there are similar large labeling errors in the test set it would ruin the leaderboard with the current metric.

How do you make sure the test set has better labeling quality?

Discussion 5 answers

@zindi, please address this. There are label errors in the training.... hope the test set is free of such errors???

11 Mar 2023, 07:42
Upvotes 8

Just to make sure label errors are expected in every labeling process. Switching the metric to MAE would reduce the impact of such errors.

Another option would be to double check the test set labels by the organizers but that could take a few hours of manual work. And as I said labeling errors are always expected :)

11 Mar 2023, 09:24
Upvotes 7

An example of very bad labelling :

12 Mar 2023, 20:08
Upvotes 9

Can we correct these errors manually or how are we supposed to correct them?

According to this we're not allowed to do so .But the problem is if the test data contains such large labeling errors it will ruin the leaderboard.

PS : Based on my experiments at least the public LB contains such errors!