MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification

By Daoyu Lin, Kun Fu, Yang Wang, Guangluan Xu, Xian Sun. 2016

186 citations recorded by the source corpus.

With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks. 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 <inline-formula> <tex-math notation="LaTeX">$G$ </tex-math></inline-formula> and a discriminative model <inline-formula> <tex-math notation="LaTeX">$D$ </tex-math></inline-formula>. We treat <inline-formula> <tex-math notation="LaTeX">$D$ </tex-math></inline-formula> 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. <inline-formula> <tex-math notation="LaTeX">$G$ </tex-math></inline-formula> can produce numerous images that are similar to the training data; therefore, <inline-formula> <tex-math notation="LaTeX">$D$ </tex-math></inline-formula> can learn better representations of remotely sensed images using the training data provided by <inline-formula> <tex-math notation="LaTeX">$G$ </tex-math></inline-formula>. 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-the-art methods.

Subfields: Computer Vision and Pattern Recognition, Ecology, Media Technology

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

In Ecology

In Media Technology

Citations in the corpus

Transformers in Vision: A Survey (2021, background): “Examples of generative approaches include conditional generation tasks such as masked image modeling [39] and image colorization [245], image super-resolution [112], image in-painting [155], and Generative Adversarial Networks– (GAN) based methods [71, 127].”
Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification (2020, methodology): “Generation-based methods include variational autoencoders [46], [47] and generative adversarial networks [48], [49].”
In-domain representation learning for remote sensing (2019, background): “An example is the multi-layer generative adversarial network (GAN) (Goodfellow et al., 2014) approach for unsupervised representation learning presented by Lin et al. (2017).”
Medical Image Synthesis with Generative Adversarial Networks for Tissue Recognition (2018, background): “applications, such as remote sensing image classification [14].”
Remote Sensing Image Scene Classification With Self-Supervised Paradigm Under Limited Labeled Samples (2020, methodology): “MATAR GANs [20] 50.”
Deep Unsupervised Embedding for Remotely Sensed Images Based on Spatially Augmented Momentum Contrast (2020, methodology): “Although Tile2Vec also exhibits positive results in ﬁve categories, the performance for the rest of the classes is rather limited, being even worse than that of the pretrained CNN + PCA and MARTA GAN in some cases.”
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, methodology): “limitations, GANs have been employed by some researchers on the field of remote sensing image scene classification [83], [84].”
A Review on Deep Learning in UAV Remote Sensing (2021, methodology): “Recently approaches in the image processing context like the classification of remote sensing images [123] and image-to-image translation problems solution [96] adopted GANs as DL model, obtaining successful results.”