MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
Open accessThe DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Abstract
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 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-the-art methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“Some approaches [4], [5] based on convolutional neural networks (CNNs) [6] have achieved success in remote sensing scene classification, but those methods usually require an enormous amount of labeled training data or are fine-tuned from pre-trained CNNs.”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
(2008) · Journal of Machine Learning Research · Cited by 33,051
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 2×
“A lot of promising recent work originates from the Skip-gram model (Mikolov et al., 2013), which inspired the skip-thought vectors (Kingma & Ba, 2015) and several techniques for unsupervised feature learning of images (Doersch et al., 2015).”
MethodLabaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 3×
“In follow-up work, a deep convolutional GAN (DCGAN) (Radford et al., 2015) performed very well in image synthesis tasks, and showed that it’s latent representation space captures important factors of variation.”
BackgroundInfluentialTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408 · cited 3×
“[13] Martın Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al.”
BackgroundMethodInfluentialBeyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Lazebnik, S., Schmid, C., & Ponce, J. (2006) · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2 (CVPR'06) · doi:10.1109/cvpr.2006.68 · Cited by 7,916
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965 · cited 1×
“A great variety of new architectural features and training procedures (Salimans et al., 2016), including feature matching and minibatch discrimination, which can produce very clean and sharp images and learn codes that contain valuable information about these textures.”
BackgroundVideo Google: a text retrieval approach to object matching in videos
Sivic, & Zisserman (2003) · Proceedings Ninth IEEE International Conference on Computer Vision · doi:10.1109/iccv.2003.1238663 · Cited by 6,367 · cited 1×
“Previously, the bag of visual words (BoVW) [1] method was frequently adopted for remote sensing scene classification.”
Method(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · cited 2×
“Another popular method is to train auto-encoders, stacking layers of denoising autoencoders (Vincent et al., 2010) which are trained locally to denoise corrupted versions of their inputs , separating the what and where components of the code (Zhao et al., 2015), ladder structures (Rasmus et al.,…”
MethodBag-of-visual-words and spatial extensions for land-use classification
Yang, Y., & Newsam, S. (2010) · Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems · doi:10.1145/1869790.1869829 · Cited by 2,969 · cited 3×
“The dataset (Yang & Newsam, 2010) consists of images of 21 land-use classes selected from aerial optical images of the US Geological Survey, taken over various regions of the United States.”
MethodUnsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629 · cited 2×
“A lot of promising recent work originates from the Skip-gram model (Mikolov et al., 2013), which inspired the skip-thought vectors (Kingma & Ba, 2015) and several techniques for unsupervised feature learning of images (Doersch et al., 2015).”
BackgroundMethodDeconvolution and Checkerboard Artifacts
Odena, A., Dumoulin, V., & Olah, C. (2016) · Distill · doi:10.23915/distill.00003 · Cited by 1,640 · cited 1×
“We set the kernel sizes to 4 × 4 and the stride to 2 in all the convolutional and deconvolutional layers, because the deconvolutional layers ca avoid uneven overlap when the kernel size is divisible by th stride [11].”
MethodInfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., & Abbeel, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.03657 · Cited by 1,156 · cited 1×
“InfoGAN (Chen et al., 2016), an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.”
MethodTowards better exploiting convolutional neural networks for remote sensing scene classification
Nogueira, K., Penatti, O. A. B., & dos Santos, J. A. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.07.001 · Cited by 902 · cited 2×
“While some of the supervised methods [4], [5] achieved an accuracy above 99%, these methods are fine-tuned from pre-trained models, which are usually trained with a large amount of labeled data (such as ImageNet).”
BackgroundDo deep features generalize from everyday objects to remote sensing and aerial scenes domains?
Penatti, O. A. B., Nogueira, K., & dos Santos, J. A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2015.7301382 · Cited by 705 · cited 10×
“51 OverFeatL + Caffe [4] Supervised 205M 99.”
BackgroundMethodResultInfluentialLearning to generate chairs with convolutional neural networks
Dosovitskiy, A., Springenberg, J. T., & Brox, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298761 · Cited by 640 · cited 2×
“a matrix multiplication, 4 but the result is reshaped into a 4-dimensional tensor and used as the start of the convolution stack. We use fractional-strided convolutions (also called deconvolutions) (Dosovitskiy et al., 2015) in our generator, allowing it to learn its own spatial upsampling, this paper uses six layers…”
MethodSheng, G., Yang, W., Xu, T., & Sun, H. (2012) · International Journal of Remote Sensing · doi:10.1080/01431161.2011.608740 · Cited by 309 · cited 2×
“As shown in Table II, our method outperforms the SCMF [14] (a sparse coding based multiple-feature fusion method) by 3.”
BackgroundMethodSemantic Annotation of Satellite Images Using Latent Dirichlet Allocation
Lienou, M., Maitre, H., & Datcu, M. (2010) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2009.2023536 · Cited by 259 · cited 1×
“The above-mentioned methods have comprised the state of the art for several years in the remote sensing community [3], but they are based on hand-crafted features, which are difficult, time-consuming, and require domain expertise to produce.”
BackgroundPyramid of Spatial Relatons for Scene-Level Land Use Classification
Chen, S., & Tian, Y. (2015) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2014.2351395 · Cited by 211
Comerford, J. M., Pooley, D., Barrows, R. S., Greene, J. E., Zakamska, N. L., Madejski, G. M., & Cooper, M. C. (2015) · The Astrophysical Journal · doi:10.1088/0004-637x/806/2/219 · Cited by 187
Hu, F., Xia, G.-S., Wang, Z., Huang, X., Zhang, L., & Sun, H. (2015) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2015.2444405 · Cited by 164 · cited 3×
“When the classification accuracy of our method is compared with LRFF [15] (an improved unsupervised feature learning algorithm based on spectral clustering), our method outperforms LRFF by more than 4%.”
MethodInfluentialMakhzani, A., & Frey, B. J. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.5663 · Cited by 137 · cited 1×
“Several unsupervised representation learning algorithms have been based on the autoencoder [7], [8], which receives corrupted data as input and is trained to predict the original, uncorrupted input.”
Evaluation of second-order visual features for land-use classification
Negrel, R., Picard, D., & Gosselin, P.-H. (2014) · 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI) · doi:10.1109/cbmi.2014.6849835 · Cited by 79
Learning LBP structure by maximizing the conditional mutual information
Ren, J., Jiang, X., & Yuan, J. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.02.001 · Cited by 78
A Hierarchical Scheme of Multiple Feature Fusion for High-Resolution Satellite Scene Categorization
Shao, W. Q., Yang, W. T., Xia, G.-S., & Liu, G. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39402-7_33 · Cited by 74
Comerford, J. M., Pooley, D. A., Barrows, R. S., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.01391 · Cited by 4
Cited by
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595
“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].”
BackgroundTransformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2021) · arXiv · doi:10.48550/arxiv.2101.01169 · Cited by 3,594
“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].”
BackgroundDeep learning in remote sensing applications: A meta-analysis and review
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., & Johnson, B. A. (2019) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.04.015 · Cited by 2,456
Cheng, G., Xie, X., Han, J., Guo, L., & Xia, G.-S. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3005403 · Cited by 995
“limitations, GANs have been employed by some researchers on the field of remote sensing image scene classification [83], [84].”
BackgroundMethodInfluentialA review on deep learning in UAV remote sensing
Osco, L. P., Marcato Junior, J., Marques Ramos, A. P., de Castro Jorge, L. A., Fatholahi, S. N., de Andrade Silva, J., Matsubara, E. T., Pistori, H., Gonçalves, W. N., & Li, J. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102456 · Cited by 458
“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.”
Method
Metadata
- Authors
- Lin, D., Fu, K., Wang, Y., Xu, G., & Sun, X.
- Affiliations
- Chinese Academy of Sciences (CN)
- Venue
- IEEE Geoscience and Remote Sensing Letters
- Published
- 2017-11
- Volume
- 14
- Issue
- 11
- Pages
- 2092-2096
- ISSN
- 1545-598X (ISSN-L)
- 1558-0571
- OpenAlex
- W2762941833
- Cited by
- 230
- References
- 30
- Citations by year
- 2026: 7 · 2025: 21 · 2024: 17 · 2023: 30 · 2022: 30 · 2021: 41 · 2020: 35 · 2019: 30 · 2018: 15 · 2017: 4
- FWCI
- 19.07
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Geoscience and Remote Sensing Letters (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (41501485, 61331017)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Social Sciences › Geography, Planning and Development › Remote Sensing and Land Use
- Keywords
- unsupervised feature learning, remote sensing image classification, generative adversarial networks, feature matching, feature extractor, unlabeled data, limited labeled data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.