ICLR Workshop Challenge #1: CGIAR Computer Vision for Crop Disease
$7,000 USD
Identify wheat rust in images from Ethiopia and Tanzania, and win a trip to present your work at ICLR 2020 in Addis Ababa.
29 January–15 March 2020 23:59
566 data scientists enrolled, 193 on the leaderboard
Quality ground truth data
published 11 Feb 2020, 13:48
edited ~4 hours later

Hello everone, I was looking to the ground truth data and I found some incosistencies. For example, in the stem_rust folder there are several images of which the ground truth label is stem_rust, but the pictures show clearly leaf_rust. For example image A0O1E2.jpg, HUYCKN.jpg, PVR11X.jpg in /stem_rust. Comparing these images with 3WPXWE.jfif, 9BEZ15.jfif in the leaf_rust folder shows that the images are almost identical still they are assigned to a different class. Does anyone know why these first ones are assigned to the stem_rust folder?

Hi i had a similar issue when i first looked at the pictures, however it was mentioned that some pictures will contain more than one instance of the classes you have to classify, one being dominant also check out this link


to get a feel of the differences and similarities between stem and leaf rust.

He.lo Eliasbayona, thanks a lot for the link, it helped at lot!