Adaptive DropBlock-Enhanced Generative Adversarial Networks for Hyperspectral Image Classification

In recent years, the hyperspectral image (HSI) classification based on generative adversarial networks (GANs) has achieved great progress. GAN-based classification methods can mitigate the limited training sample dilemma to some extent. However, several studies have pointed out that existing GAN-based HSI classification methods are heavily affected by the imbalanced training data problem. The discriminator in GAN always contradicts itself and tries to associate fake labels to the minority-class samples and, thus, impair the classification performance. Another critical issue is the mode collapse in GAN-based methods. The generator is only capable of producing samples within a narrow scope of the data space, which severely hinders the advancement of GAN-based HSI classification methods. In this article, we proposed an Adaptive DropBlock-enhanced Generative Adversarial Networks (ADGANs) for HSI classification. First, to solve the imbalanced training data problem, we adjust the discriminator to be a single classifier, and it will not contradict itself. Second, an adaptive DropBlock (AdapDrop) is proposed as a regularization method employed in the generator and discriminator to alleviate the mode collapse issue. The AdapDrop generated drop masks with adaptive shapes instead of a fixed size region, and it alleviates the limitations of DropBlock in dealing with ground objects with various shapes. Experimental results on three HSI data sets demonstrated that the proposed ADGAN achieved superior performance over state-of-the-art GAN-based methods. Our codes are available at https://github.com/summitgao/HC_ADGAN.

Automated summary

This article proposes an Adaptive DropBlock-enhanced Generative Adversarial Networks (ADGANs) for HSI classification, addressing the imbalanced training data and mode collapse issues through adjustments in the discriminator and the introduction of adaptive DropBlock. Experimental results demonstrate superior performance over existing GAN-based methods.