MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification

Abstract

Abstract-With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks (CNNs). However, due to the limited amount of labeled data available, supervised learning is often difficult to carry out. Therefore, we proposed an unsupervised model called multiple-layer feature-matching generative adversarial networks (MARTA GANs) to learn a representation using only unlabeled data. MARTA GANs consists of both a generative model G and a discriminative model D. We treat D as a feature extractor. To fit the complex properties of remote sensing data, we use a fusion layer to merge the mid-level and global features. G can produce numerous images that are similar to the training data; therefore, D can learn better representations of remotely sensed images using the training data provided by G. The classification results on two widely used remote sensing image databases show that the proposed method significantly improves the classification performance compared with other state-of-theart methods.

An End-to-End Joint Unsupervised Learning of Deep Model and Pseudo-Classes for Remote Sensing Scene Representation

“…When compared with other deep models, the proposed method can obtain comparable results. The proposed method can obtain 87.74% which is better than 86% obtained by CNN-1 [19] and 87.69% by MARTA GANs without data augmentation [1], [18]. It can obtain comparable results when compared with UCFFN (87.83%).…”

“…Accuracy(%) Dense SIFT [14] 81.67 ± 1.23 SPCK++ [15] 76.05 UFL-SC [16] 90.26 ± 1.51 COPD [17] 91.33 ± 1.11 MARTA GANs (without data augmentation) [1], [18] 85.37 CNN-1 [19] 84.53 UCFFN [1] 88.57 Proposed Method 94.33 ± 1.06…”

Region-Wise Deep Feature Representation for Remote Sensing Images

“…Other related works such as [44] also report measures that derive from the confusion matrix, in which the Bradley-Terry Model was used to quantify association in remotely sensed images. In order for fair comparison with the reported results in previous remote sensing image classification works [19,32,[35][36][37], we adopt the same accuracy assessment measures used in the above literature. Table 1 shows the overall accuracy of classification results for different remote sensing image feature learning methods.…”

Siamese-GAN: Learning Invariant Representations for Aerial Vehicle Image Categorization

“…For instance, Deep Convolutional GANs (DCGANs) [38] were designed to allow the network to generate data with similar internal structure as training data, improving the quality of the generated images, and Conditional GANs [39] add an additional conditioning variable to both the generator and the discriminator. Based on the previous architectures the concept of GANs has been adopted to solve many computer visions related tasks such as image generation [40,41], image super-resolution [42], unsupervised learning [43], semi-supervised learning [44], and image painting and colorization [45,46].…”

“…In the context of remote sensing, Lin et al [43] used GANs for unsupervised scene classification. The model consists of a generator that learns to produce additional training images similar to the real data, and a discriminator that works as a feature extractor, which learns better representations of the images using the data provided by the generator.…”