Small sample classification of hyperspectral image using model-agnostic meta-learning algorithm and convolutional neural network

ABSTRACT

The difficulties of obtaining sufficient high-quality labelled samples have always been one of the important factors hindering the practical application of hyperspectral images (HSI) classification. The regular deep learning models only attempt to mine the discriminant and informative features in the target HSI. Therefore, the satisfactory results cannot be obtained with only a few labelled samples because their huge parameter space cannot be fully trained. To this end, a simple and effective framework is proposed utilizing the idea of meta-learning to improve HSI classification performance under the condition of small sample. Specifically, we design a simple model by stacking convolutional blocks, and introduce a model-agnostic meta-learning algorithm (MAML) to enable the model to implement meta-optimization on vast different tasks. The MAML algorithm can enable the model to acquire the more general-purpose representations, so as to adapt quickly to new tasks with only a few labelled samples and a small number of gradient update steps. To improve the practical value of the research, two kinds of classification scenarios, cross-data small sample classification on the same HSI and cross-scene small sample classification between different HSI, are designed for experiments. The results on three public HSI demonstrate that our method outperform the state-of-the-art methods in both scenarios. In addition, the proposed method, actually an optimization-based meta-learning method, provides a new idea for HSI small sample classification.

Acknowledgements

We gratefully acknowledge the financial support offered to this research by the National Natural Science Foundation of China (Grants Nr. 41801388). We would also like to thank all the researchers for kindly providing the codes associated with the experiments.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This research was funded by National Natural Science Foundation of China [41801388].