MapAI Competition Submission for Team Kaborg
Using stable diffusion for ML image augmentation
DOI:
https://doi.org/10.5617/nmi.10150Emneord (Nøkkelord):
artificial intelligence, map segmentation, deep learning, dataset augmentationSammendrag
This paper constitutes the final portion of our submission to
the MapAI image segmentation competition [1]. We introduce
a Stable Diffusion(SD) [2] model with a particular emphasis
on augmenting image segmentation datasets. Due to an
unfortunate mistake made during the training of our model
iterations, the benefits of these techniques are not reflected in
the final submission score. We reach only a combined score
of 0.62. Nevertheless, the method shows potential and can be
applied to accurate image segmentation in future projects
Nedlastinger
Publisert
2023-03-27
Utgave
Seksjon
NMI Challenge
Lisens
Opphavsrett 2022 Nordic Machine Intelligence
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
Dette verket er lisensiert under Creative Commons Attribution 4.0 International License.