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.

Semantic-Fusion Gans for Semi-Supervised Satellite Image Classification / Roy, Subhankar; Sangineto, E.; Demir, B.; Sebe, N.. - (2018), pp. 684-688. (Intervento presentato al convegno ICIP tenutosi a Athens nel 2018) [10.1109/ICIP.2018.8451836].

Semantic-Fusion Gans for Semi-Supervised Satellite Image Classification

Roy, Subhankar;E. Sangineto;B. Demir;N. Sebe
2018-01-01

Abstract

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.
2018
2018 25th IEEE International Conference on Image Processing (ICIP)
Roy, Subhankar
New York
IEEE
978-1-4799-7061-2
Roy, Subhankar; Sangineto, E.; Demir, B.; Sebe, N.
Semantic-Fusion Gans for Semi-Supervised Satellite Image Classification / Roy, Subhankar; Sangineto, E.; Demir, B.; Sebe, N.. - (2018), pp. 684-688. (Intervento presentato al convegno ICIP tenutosi a Athens nel 2018) [10.1109/ICIP.2018.8451836].
File in questo prodotto:
File Dimensione Formato  
08451836.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.54 MB
Formato Adobe PDF
1.54 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/215312
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 31
  • ???jsp.display-item.citation.isi??? 25
social impact