search

feevos / resuneta

mxnet source code for the resuneta semantic segmentation models
Other
131 stars 30 forks source link

Postprocessing. #11

Open Akhilesh64 opened 3 years ago

Akhilesh64 commented 3 years ago

What postprocessing steps have you used after getting model output, especially for boundary detection. Could you please share the scripts, it would be a huge help.

feevos commented 3 years ago

Hi @Akhilesh64 , the information you request are for another work that is not included in this repository, however you can find much more information (and better models) in our latest paper - published 2 days ago, here: https://www.mdpi.com/2072-4292/13/11/2197 source code (includes some post processing): https://github.com/waldnerf/decode

Check also the change detection paper (under review), that has all modelling characteristics and focuses on the deep learning aspects of the modelling process ( https://github.com/feevos/ceecnet ) - hint: change detection = two images on input, single semantic segmentation mask on output.

Regards