Semantic-Fusion Gans for Semi-Supervised Satellite Image Classification
By Subhankar Roy, Enver Sangineto, Nicu Sebe, Begüm Demir. 2018
34 citations recorded by the source corpus.
Most of the public satellite image datasets contain only a small number of annotated images. The lack of a sufficient quantity of labeled data for training is a bottleneck for the use of modern deep-learning based classification approaches in this domain. In this paper we propose a semi -supervised approach to deal with this problem. We use the discriminator $(D)$ of a Generative Adversarial Network (GAN) as the final classifier, and we train $D$ using both labeled and unlabeled data. The main novelty we introduce is the representation of the visual information fed to $D$ by means of two different channels: the original image and its “semantic” representation, the latter being obtained by means of an external network trained on ImageNet. The two channels are fused in $D$ and jointly used to classify fake images, real labeled and real unlabeled images. We show that using only 100 labeled images, the proposed approach achieves an accuracy close to 69% and a significant improvement with respect to other GAN-based semi-supervised methods. Although we have tested our approach only on satellite images, we do not use any domain-specific knowledge. Thus, our method can be applied to other semi-supervised domains.
Subfields: Computer Vision and Pattern Recognition, Media Technology, Generative Models, Remote Sensing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Nicu Sebe
- Elisa Ricci
- Aliaksandr Siarohin
- Sergey Tulyakov
- Stéphane Lathuilière
- Jian Zhao
- Luc Van Gool
- Xiaogang Wang
In Media Technology
- Elisa Ricci
- Nicu Sebe
- Aliaksandr Siarohin
- Sergey Tulyakov
- Stéphane Lathuilière
- Peter Wonka
- Ibraheem Alhashim
In Generative Models
Citations in the corpus
- Animating Arbitrary Objects via Deep Motion Transfer (2018, methodology): “Several methods derived from Generative Adversarial Networks (GAN) [16] and Variational Autoencoders (VAE) [24] have been proposed to generate images and videos [19, 32, 30, 39, 29, 37, 36, 33].”