Recently, deep learning-based methods outperform others in hyperspectral image (HSI) classification. However, the deep learning methods require sufficient labeled samples to improve performance, which is unfeasible in practice. The training labels are usually limited in HSIs that need to be classified (namely target domain), while other available labels in multisource HSIs (namely source domain) are not utilized effectively. To mitigate these issues, an attention multisource fusion method of few-shot learning (AMF-FSL) is proposed for small-sized HSI classification. AMF-FSL is an implementation of few-shot learning (FSL) in the meta-learning field, which can transfer the learned ability of classification from multiple source data to target data. The process of learning to classify in AMF-FSL is not restricted by the traditional requirement of the same distribution between the source and target domains, which can learn from the source domain and apply it to a different distribution in the target domain. Moreover, the multisource domain adaption in AMF-FSL has the capacity of extracting features from fused homogeneous and heterogeneous data in the source domain, which can improve the generalization of the classification model in the cross domains. Specifically, the multisource domain adaption contains three modules, namely the target-based class alignment, domain attention assignment, and multisource data fusion, which are responsible for aligning the class space, paying band-level attention, and merging the distributions of homogeneous and heterogeneous data in the source domain. The experimental results demonstrate the effectiveness of the multisource domain adaption and the superiority of AMF-FSL over other state-of-theart methods in small-sized HSI classification.
The distinction of similar classes has always been the core issue in image classification. In this paper, a new hierarchical classification process based on three-dimensional attention soft augmentation (HC-3DAA) is proposed to improve the accuracy of classifiers, especially for the accuracy between similar classes. In HC-3DAA processing, the merging matrix is firstly constructed based on the validation confusion matrix to measure the similarity among different classes. Specifically, the 3D attention soft augmentation module combined with CutMix is designed for guiding the network model to focus on the key discriminative features. Then the extracted 3D feature differences between similar classes are inserted into the attention module for the reclassification to get higher classification accuracy. To evaluate the performance of HC-3DAA, CutMix models with different feature dimensions and the hierarchical classification module are separately discussed on two widely used hyperspectral datasets. Two different classifiers 3D-CNN and ResNet are included in the comparative analysis. Besides, experimental results also demonstrate that the proposed HC-3DAA outperforms several state-of-the-art attention-based methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.