Classification of Hyperspectral Images Based on Multiclass Spatial–Spectral Generative Adversarial Networks

Feng, Jie; Hyeong-keun, Yu; Wang, Lin; Cao, Xin; Zhang, Xiangrong; Jiao, Licheng

doi:10.1109/tgrs.2019.2899057

Cited by 130 publications

(72 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies revealed that the generated samples promote the discriminator's classification ability through adversarial learning, especially in the case of small samples size (10,11,15) and feature matching is able to improve classification performance (10). Thus, we attempt to apply Feature Matching GAN based on FNC to discriminate MDD vs HC and SZ vs HC.…”

Section: Activations In An Intermediate Layer Of the Discriminatormentioning

confidence: 99%

“…In particular, generative adversarial networks (GANs) have drawn increasing attention due to their capability to perform data generation and have been widely used in many fields, including image synthesis, reconstruction, segmentation, and classification (9). GANs have been recently proven successful on standard classification benchmark tasks (10,11). The generated samples promote the discriminator's classification ability through adversarial learning, especially in the case of small samples size.…”

Section: Introductionmentioning

confidence: 99%

“…The generated samples promote the discriminator's classification ability through adversarial learning, especially in the case of small samples size. For instance, (11) proposed multiclass spatial-spectral GAN (MSGAN), the discriminator enhances classification performance by extracting the joint features of spatial and spectral information generated by two generators. The features for these problems are high-dimensional but the small sample size problem in medical imaging makes it challenging for the classifiers to learn a good decision boundary.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Functional Network Connectivity (Fnc)-Based Generative Adversarial Network (Gan) and Its Applications in Classification of Mental Disorders

Zhao

Zhi²,

Yan³

et al. 2019

Preprint

View full text Add to dashboard Cite

ABSTRACTFunctional network connectivity (FNC) obtained from resting-state functional magnetic resonance imaging (fMRI) data have been commonly used to study mental disorders in neuroimaging applications. Likewise, generative adversarial networks (GANs) have performed well in multiple classification benchmark tasks. However, the application of GANs to fMRI is relatively rare. In this work, we proposed an FNC-based GAN for classifying brain disorders from healthy controls (HCs), in which FNC matrices were calculated by correlation of time courses derived from non-artefactual fMRI independent components (ICs). The proposed GAN model consisted of one discriminator (real FNCs) and one generator (fake FNCs), each has four fully-connected layers, and feature matching was implemented between each other to improve classification performance. An average accuracy of 70.1% with 10-fold cross-validation was achieved for classifying 269 major depressive disorder (MDD) patients from 286 HCs, at least 5.9% higher compared to other 6 popular classification approaches (54.5-64.2%). In another application to discriminating between 558 schizophrenia patients and 542 HCs from 7 sites, the proposed GAN model achieved 80.7% accuracy in leave-one-site-out prediction, outperforming support vector machine (SVM) and deep neural net (DNN) by 3-6%. To the best of our knowledge, this is the first attempt to apply GAN model based on fMRI data for mental disorder classification. Such a framework promises wide utility and great potential in neuroimaging biomarker identification.

show abstract

Section: Activations In An Intermediate Layer Of the Discriminatormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Functional Network Connectivity (Fnc)-Based Generative Adversarial Network (Gan) and Its Applications in Classification of Mental Disorders

Zhao

Zhi²,

Yan³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Although the classification results obtained by these methods may not be good enough, this is a successful attempt to apply the machine learning method to hyperspectral remote sensing. Lately, spatial structure information has been gradually taken into account in some pixel-based classification approaches [13][14][15][16][17][18][19][20], aiming at getting better classification results. Generally speaking, the purpose of introducing spatial information into the process of classification can be roughly understood as denoising HSI in preprocessing [21][22][23][24], defining the novel similarity between a pair of pixels [25,26], reducing dimensionality [27], improving the classification map in post-processing [28][29][30], or their combinations.…”

Section: Introductionmentioning

confidence: 99%

A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level

et al. 2020

View full text Add to dashboard Cite

Although superpixel segmentation provides a powerful tool for hyperspectral image (HSI) classification, it is still a challenging problem to classify an HSI at superpixel level because of the characteristics of adaptive size and shape of superpixels. Furthermore, these characteristics of superpixels along with the appearance of noisy pixels makes it difficult to appropriately measure the similarity between two superpixels. Under the assumption that pixels within a superpixel belong to the same class with a high probability, this paper proposes a novel spectral–spatial HSI classification method at superpixel level (SSC-SL). Firstly, a simple linear iterative clustering (SLIC) algorithm is improved by introducing a new similarity and a ranking technique. The improved SLIC, specifically designed for HSI, can straightly segment HSI with arbitrary dimensionality into superpixels, without consulting principal component analysis beforehand. In addition, a superpixel-to-superpixel similarity is newly introduced. The defined similarity is independent of the shape of superpixel, and the influence of noisy pixels on the similarity is weakened. Finally, the classification task is accomplished by labeling each unlabeled superpixel according to the nearest labeled superpixel. In the proposed superpixel-level classification scheme, each superpixel is regarded as a sample. This obviously greatly reduces the data volume to be classified. The experimental results on three real hyperspectral datasets demonstrate the superiority of the proposed spectral–spatial classification method over several comparative state-of-the-art classification approaches, in terms of classification accuracy.

show abstract

“…Zhan et al [8] proposed HSGAN for semisupervised hyperspectral image classification. MSGAN proposed by Feng et al [9] acquired high classification accuracy by utilizing a small amount of data. Ultimately, the discriminators of their models play a major role in the classification task, but as the main function of GAN model, the generator should achieve better performance in the field of hyperspectral sample generation.…”

Section: Introductionmentioning

confidence: 99%

Cascade conditional generative adversarial nets for spatial-spectral hyperspectral sample generation

Liu

Qiao

Xiong

et al. 2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

Classification of Hyperspectral Images Based on Multiclass Spatial–Spectral Generative Adversarial Networks

Cited by 130 publications

References 36 publications

Functional Network Connectivity (Fnc)-Based Generative Adversarial Network (Gan) and Its Applications in Classification of Mental Disorders

Functional Network Connectivity (Fnc)-Based Generative Adversarial Network (Gan) and Its Applications in Classification of Mental Disorders

A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level

Cascade conditional generative adversarial nets for spatial-spectral hyperspectral sample generation

Contact Info

Product

Resources

About