Meihong Liu

Aiming at few-shot classification in the field of hyperspectral remote sensing images, this paper proposes a classification method based on cross-scene adaptive learning. First, based on the unsupervised domain adaptive technology, cross-scene knowledge transfer learning is carried out to reduce the differences between source scene and target scene. At the same time, depthwise over-parameterized convolution is used in the deep embedding model to improve the convergence speed and feature extraction ability. Second, two symmetrical subnetworks are designed in the model to further reduce the differences between source scene and target scene. Then, Manhattan distance is learned in the Manhattan metric space in order to reduce the computational cost of the model. Finally, the weighted K-nearest neighbor is introduced for classification, in which the weighted Manhattan metric distance is assigned to the clustered samples to improve the processing ability to the imbalanced hyperspectral image data. The effectiveness of the proposed algorithm is verified on the Pavia and Indiana hyperspectral dataset. The overall classification accuracy is 90.90% and 65.01%. Compared with six other kinds of hyperspectral image classification methods, the proposed cross-scene method has better classification accuracy.

Although hyperspectral data provide rich feature information and are widely used in other fields, the data are still scarce. Training small sample data classification is still a major challenge for HSI classification based on deep learning. Recently, the method of mining sample relationships has been proved to be an effective method for training small samples. However, this strategy requires high computational power, which will increase the difficulty of network model training. This paper proposes a modified depthwise separable relational network to deeply capture the similarity between samples. In addition, in order to effectively mine the similarity between samples, the feature vectors of support samples and query samples are symmetrically spliced. According to the metric distance between symmetrical structures, the dependence of the model on samples can be effectively reduced. Firstly, in order to improve the training efficiency of the model, depthwise separable convolution is introduced to reduce the computational cost of the model. Secondly, the Leaky-ReLU function effectively activates all neurons in each layer of neural network to improve the training efficiency of the model. Finally, the cosine annealing learning rate adjustment strategy is introduced to avoid the model falling into the local optimal solution and enhance the robustness of the model. The experimental results on two widely used hyperspectral remote sensing image data sets (Pavia University and Kennedy Space Center) show that compared with seven other advanced classification methods, the proposed method achieves better classification accuracy under the condition of limited training samples.

The predecessor of China Optics was China Optics and Applied Optics Digest, which was founded in 1985. At that time, it was the only retrieval journal in the field of optics in China. At the end of 2008, China Optics and Applied Optics Digest was renamed 《中国光学》的前身是1985年创办的《中国光学与应用光学文摘》，当时是国内光学领域唯一的检索刊物。2008年底《中国光学与应用光学文摘》转型更名为《中国光学与应用光学》期刊，刊载内容突破了文摘的限制，正式成为学术刊物。