As one of the most popular topics in polarimetric synthetic aperture radar (PolSAR) community, PolSAR image classification has always been an important way for PolSAR applications. Constructing representations is the most critical part of PolSAR image classification. With the maturity of deep learning technique, many data-driven PolSAR representation methods have been proposed, most of which are based on convolutional neural networks (CNNs). Despite some achievements, the bottleneck of CNN-based methods may be related to the locality induced by their inductive biases. Considering this problem, the state-of-the-art method in natural language processing, i.e., transformer, is introduced into PolSAR image classification for the first time. Specifically, a vision transformer (ViT)-based representation learning framework is proposed in this article, which covers both supervised learning and unsupervised learning. For supervised learning, we use self-attention to replace convolution, which shifts the focus from the information in local neighborhoods to the long-range interactions between each pixel. Beyond supervised learning, we introduce an improved contrastive-based strategy to implement simple unsupervised representation learning. Compared with CNN and its variants, ViT constructs more global representations by explicitly modeling the relationship between each pixel, so as to improve the classification performance. Experimental results on four widely used PolSAR image datasets indicate that the representation obtained by the ViT-based methods is better for PolSAR image classification, whether supervised (up to about 5% accuracy improvement) or unsupervised (up to about 4%). In addition, we also prove the robustness of ViT to the initial input form. These discoveries may arouse rethinking of the dominance of CNNs in PolSAR image classification.

Convolutional neural networks (CNNs) have shown good performance in polarimetric synthetic aperture radar (PolSAR) image classification. Excellent hand-crafted CNN architectures incorporated the wisdom of human experts, which is an important reason for CNNs success. However, the design of architectures is a difficult problem, which needs a lot of professional knowledge as well as computational resources. Moreover, the manually designed architecture might be suboptimal, because it is only one of the thousands of unobserved but objective existed paths. Considering that the success of deep learning is largely due to its automation of the feature engineering process, how to design automatic architecture search methods to replace the hand-crafted ones is an interesting topic. In this article, the application of neural architecture search (NAS) in the PolSAR area is explored for the first time. Different from the utilization of existing methods, a PolSAR-tailored Differentiable Architecture Search (DARTS) method, called PDAS, is proposed in order to adapt NAS to the PolSAR classification. A PolSAR-tailored search space and an improved one-shot search strategy are equipped with the proposed method. By PDAS, the architecture (corresponds to the hyperparameter but not the topology) parameters can be optimized with high efficiency by a stochastic gradient descent (SGD) method. The optimized architecture parameters should be transformed into corresponding architecture and retrained to achieve classification. In addition, a complex-valued PDAS (CVPDAS) is developed to fit the data form of PolSAR images so as to improve the performance. Experiments on three benchmark data sets show that the architectures obtained by searching have better classification performance than hand-crafted ones.

Convolutional neural networks (CNNs) have become the state-of-the-art in optical image processing. Recently, CNNs have been used in polarimetric synthetic aperture radar (PolSAR) image classification and obtained promising results. Unlike optical images, the unique phase information of PolSAR data expresses the structure information of objects. This special data representation makes 3D convolution which explicitly modeling the relationship between polarimetric channels perform better in the task of PolSAR image classification. However, the development of deep 3D-CNNs will cause a huge number of model parameters and expensive computational costs, which not only leads to the decrease of the interpretation speed during testing, but also greatly increases the risk of over-fitting. To alleviate this problem, a lightweight 3D-CNN framework that compresses 3D-CNNs from two aspects is proposed in this paper. Lightweight convolution operations, i.e., pseudo-3D and 3D-depthwise separable convolutions, are considered as low-latency replacements for vanilla 3D convolution. Further, fully connected layers are replaced by global average pooling to reduce the number of model parameters so as to save the memory. Under the specific classification task, the proposed methods can reduce up to 69.83% of the model parameters in convolution layers of the 3D-CNN as well as almost all the model parameters in fully connected layers, which ensures the fast PolSAR interpretation. Experiments on three PolSAR benchmark datasets, i.e., AIRSAR Flevoland, ESAR Oberpfaffenhofen, EMISAR Foulum, show that the proposed lightweight architectures can not only maintain but also slightly improve the accuracy under various criteria.

Deep learning and convolutional neural networks (CNNs) have made progress in polarimetric synthetic aperture radar (PolSAR) image classification over the past few years. However, a crucial issue has not been addressed, i.e., the requirement of CNNs for abundant labeled samples versus the insufficient human annotations of PolSAR images. It is well known that following the supervised learning paradigm may lead to the overfitting of training data, and the lack of supervision information of PolSAR images undoubtedly aggravates this problem, which greatly affects the generalization performance of CNN-based classifiers in large-scale applications. To handle this problem, in this article, learning transferrable representations from unlabeled PolSAR data through convolutional architectures is explored for the first time. Specifically, a PolSAR-tailored contrastive learning network (PCLNet) is proposed for unsupervised deep PolSAR representation learning and few-shot classification. Different from the utilization of optical processing methods, a diversity stimulation mechanism is constructed to narrow the application gap between optics and PolSAR. Beyond the conventional supervised methods, PCLNet develops an unsupervised pretraining phase based on the proxy objective of instance discrimination to learn useful representations from unlabeled PolSAR data. The acquired representations are transferred to the downstream task, i.e., few-shot PolSAR classification. Experiments on two widely used PolSAR benchmark data sets confirm the validity of PCLNet. Besides, this work may enlighten how to efficiently utilize the massive unlabeled PolSAR data to alleviate the greedy demands of CNN-based methods for human annotations.

Noting the fact that the high-dimensional data composed of various polarimetric features has better decouplability than polarimetric synthetic aperture radar (PolSAR) image source data, in this letter, multiple polarimetric features are extracted and stacked to form a high-dimensional feature cube as the input of convolutional neural networks (CNNs) to improve the performance of PolSAR image classification. Directly utilizing the polarimetric features will produce a performance degradation and the recalibration of them is indispensable. However, classical feature selection methods are independent of the classifier, which means that the stimulated features may not be the classification-friendly ones. To avoid separated procedures and improve the performance, attention-based polarimetric feature selection convolutional network, called AFS-CNN, is proposed to implement end-to-end feature selection and classification. The relationship between input polarimetric features can be captured and embedded through attention-based architecture to ensure the validity of high-dimensional data classification. Experiments on two PolSAR benchmark data sets verify the performance of the proposed method. Furthermore, this work is quite flexible, which is reflected in that the proposal can be used as a plug-and-play component of any CNN-based PolSAR classifier.

In recent years, significant research has been conducted on utilizing simulated data to support Synthetic Aperture Radar Automatic Target Recognition (SAR-ATR) based on deep learning techniques. By distilling the dark knowledge extracted from simulated samples, quality of the learned representations on measured samples can be effectively enhanced. However, our study highlights an important oversight in previous works: unquestioning trust on all simulated samples inevitably introduces the part of dark knowledge that is detrimental to SAR-ATR performance. To address this issue, we introduce evidential learning to estimate the confidence degree of the model after inputting simulated samples, thereby assessing the validity of the dark knowledge to be distilled. Then, the simulated-measured knowledge distillation process will be carried out in a trusted manner. Specifically, we encourage the model to prioritize distilling the dark knowledge with higher validity while avoiding the influence of inferior knowledge through a dynamic confidence weighting method. Additionally, we transform the standard logits-based knowledge distillation loss function into a feature-based one, giving the proposed method the ability to plug-and-play. The above aspects constitute the proposed trusted simulated-measured knowledge distillation method for SAR-ATR. Multiple comparative studies on the Simulated And Measured Paired Labeled Experiment (SAMPLE) dataset demonstrate the effectiveness of our proposed method, which not only achieves superior performance but also maintains the desired computational complexity in the inference phase.