Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN
1
Department of Engineering, Aarhus University, Finlandsgade 22, DK-8200 Aarhus N, Denmark
2
Department of Agroecology, Aarhus University, Forsøgsvej 1, DK-4200 Slagelse, Denmark
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(22), 2671; https://doi.org/10.3390/rs11222671
Received: 7 October 2019
/
Revised: 6 November 2019
/
Accepted: 13 November 2019
/
Published: 15 November 2019
(This article belongs to the Section Remote Sensing in Agriculture and Vegetation)
Lack of annotated data for training of deep learning systems is a challenge for many visual recognition tasks. This is especially true for domain-specific applications, such as plant detection and recognition, where the annotation process can be both time-consuming and error-prone. Generative models can be used to alleviate this issue by producing artificial data that mimic properties of real data. This work presents a semi-supervised generative adversarial network (GAN) model to produce artificial samples of plant seedlings. By applying the semi-supervised approach, we are able to produce visually distinct samples for nine unique plant species using a single GAN model, while still maintaining a relatively high visual variance in the produced samples for each species. Additionally, we are able to control the appearance of the generated samples with respect to rotation and size through a set of latent variables, despite these not being annotated features in the training data. The generated samples resemble the intended species with an average recognition accuracy of ∼64.3%, evaluated using an external state-of-the-art plant seedling classification model. Additionally, we explore the potential of using the GAN model’s discriminator as a quality assessment tool to remove poor representations of plant seedlings from the artificial samples.
View Full-Text
Keywords:
generative model; generative adversarial networks; supervised learning; unsupervised learning
▼
Show Figures
Graphical abstract
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
MDPI and ACS Style
Madsen, S.L.; Mortensen, A.K.; Jørgensen, R.N.; Karstoft, H. Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN. Remote Sens. 2019, 11, 2671. https://doi.org/10.3390/rs11222671
AMA Style
Madsen SL, Mortensen AK, Jørgensen RN, Karstoft H. Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN. Remote Sensing. 2019; 11(22):2671. https://doi.org/10.3390/rs11222671
Chicago/Turabian StyleMadsen, Simon Leminen, Anders Krogh Mortensen, Rasmus Nyholm Jørgensen, and Henrik Karstoft. 2019. "Disentangling Information in Artificial Images of Plant Seedlings Using Semi-Supervised GAN" Remote Sensing 11, no. 22: 2671. https://doi.org/10.3390/rs11222671
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
