王梓祺, 李阳, 张睿, 王家宝, 李允臣, 陈瑶(陆军工程大学)
Few-shot SAR image classification: a survey
Wang Ziqi, Li Yang, Zhang Rui, Wang Jiabao, Li Yunchen, Chen Yao(Army Engineering University of PLA)
Few-shot SAR image classification aims to use a small number of training samples to classify new SAR images and facilitate the subsequent vision tasks further. In recent years, it has received widespread attention in the field of image processing, especially playing a crucial role in tasks such as environmental monitoring, target reconnaissance, and geological exploration. Moreover，the growth of deep learning has been promoting deep learning-based few-shot SAR image classification. In particular, the improvement of few-shot learning algorithm, such as the attention mechanism, transfer learning, and meta learning, has led to a qualitative leap in few-shot SAR image classification performance. However, it is necessary to conduct a comprehensive review and analysis of state-of-the-art deep learning-based few-shot SAR image classification algorithms for different complex scenes. Thus, we develop a systematic and critical review to explore the developments of few-shot SAR image classification in recent years. First, a comprehensive and systematic introduction of the few-shot SAR image classification field is presented from the following three aspects: 1) overview of early SAR image classification methods, 2) the existing dataset, 3) the prevailing evaluation metrics. Then, the existing few-shot SAR image classification methods were categorized into four types: transfer learning methods, meta learning methods, metric learning methods, and comprehensive methods. The main contributions and the datasets used for each method were summarized. Therefore, we tested the classification accuracy and runtime of 16 classic few-shot visible light image classification methods on the MSTAR dataset. In this way, the evaluation benchmark for few-shot SAR image classification methods is supplemented for future research reference. Finally, the summary and challenges in the few-shot SAR image classification community are highlighted. In particular, some prospects are recommended further in the field of few-shot SAR image classification. First of all, starting from the classification criteria, SAR image classification methods can be divided into four categories based on the feature information used, whether manual sample labeling is required, technical methods, and processing objects. These traditional SAR image classification methods lay the foundation for subsequent few-shot SAR image classification methods. We briefly introduce the popular public datasets and prevailing evaluation metrics. The existing datasets for few-shot SAR image classification include: MSTAR, OpenSARShip, COSMO-SkyMed, FuSAR-Ship, OpenSARUrban, and SAR-ACD. Among them, MSTAR is the most commonly used standard few-shot SAR image classification dataset. The evaluation indicators for method performance in few-shot SAR image classification tasks mainly include classification accuracy, precision, and recall. Due to the fact that precision and recall represent two different indicators, it is difficult to intuitively reflect the performance of the model. Therefore, the harmonic mean of these two indicators has become a direct indicator for judging the performance of the model. In addition, few-shot learning also commonly uses top-1 and top-5 as evaluation indicators. Secondly, few-shot SAR image classification methods based on deep learning can be divided into three categories: transfer learning, meta learning, and metric learning. Transfer learning methods quickly adapt to the new class image classification by using the association between similar tasks to assist the model after completing the pre-training on a large number of base class data. This type of method can effectively overcome the problem of insufficient training samples in the field of SAR images. Meta learning methods aim to enable models to learn by training a meta learner to evaluate the dataset learning process and gain learning experience. Then, the model utilizes the acquired learning experience to complete relevant classification tasks on the target dataset. Metric learning methods are an end-to-end training approach that utilizes data from each K-shot category to learn a feature embedding space. In this feature embedding space, the model can more effectively measure the similarity between samples. This type of method relatively reduces the difficulty of training feature extractors, making the structure of the model more flexible and able to quickly adapt to the task of identifying new classes. Due to the different imaging principles between SAR images and visible light images, some comprehensive methods guided by physical knowledge and domain knowledge have also been used in SAR image classification tasks and achieved great results. Therefore, in addition to the above three classification methods, some methods that combine deep learning and SAR image characteristics have also been applied to solve the problem of few-shot SAR image classification. Especially, we summarize the limitations of different few-shot SAR image classification algorithms and provide some recommendations for further research. Thirdly, we tested the classification performance of 16 visible light dataset methods migrating to SAR image datasets within a unified framework, and comprehensively evaluated the transfer effect of few-shot learning models from two aspects: classification accuracy and runtime. This work can effectively supplement the evaluation benchmark for few-shot SAR image classification tasks. The experiment found that the few-shot learning method based on metric learning achieved good performance in the field of SAR image classification without comprehensive methods. Finally, the review summarizes the future development trends and challenges of few-shot SAR image classification based on a summary of existing methods.