🌱 Must-Read: rgn images should be removed?

Microsoft Rice Disease Classification Challenge

Helping Egypt

$3 000 USD

Challenge completed ~3 years ago

Skills you will learn

Classification

Computer Vision

916 joined

260 active

Info Data Chat Leaderboard

Start

May 13, 22

Aug 14, 22

Reveal

Aug 14, 22

Shuaib_Aslam

rgn images should be removed?

Data · 24 Jul 2022, 13:37 · 3

Do we have to remove rgn images before training? I can see rgn images are not included in testing csv and submittion csv files. Why to include rgn images and why not?

Discussion 3 answers

TheVeloper

Redeemer's university

I belive the rgn images were given to provide extra information. It's your choice to remove them before training or not(mindful of possible leakage). You can find a way to blend the rgn images into your solution.

24 Jul 2022, 14:04

Upvotes 1

Koleshjr

Multimedia university of kenya

Tbh removing the rgn images makes the lb score worse while the local validation is good. I don't know why we are having a bad lb score while removing the rgn and we dont have rgn images in the sample submission. Any explanations?

replied to TheVeloper24 Jul 2022, 15:53

Upvotes 0

poppingtonic

As @TheVeloper said, you can blend them somehow. I thought about this early on when I joined in the competition and came up with this method: https://github.com/poppingtonic/semisupervised-rice-africa

I released one of the encoders I pretrained during my runs with this particular architecture (xresnet34), linked to in the repo, in case you want to try it out in your own setup.

24 Jul 2022, 15:23

Upvotes 1

Join the largest network for
data scientists and AI builders

About FAQs

Status