Ship detection is a challenging task for synthetic aperture radar (SAR) images. Ships have arbitrary directionality and multiple scales in SAR images. Furthermore, there is a lot of clutter near the ships. Traditional detection algorithms are not robust to these situations and easily cause redundancy in the detection area. With the continuous improvement in resolution, the traditional algorithms cannot achieve high-precision ship detection in SAR images. An increasing number of deep learning algorithms have been applied to SAR ship detection. In this study, a new ship detection network, known as the instance segmentation assisted ship detection network (ISASDNet), is presented. ISASDNet is a two-stage detection network with two branches. A branch is called an object branch and can extract object-level information to obtain positioning bounding boxes and classification results. Another branch called the pixel branch can be utilized for instance segmentation. In the pixel branch, the designed global relational inference layer maps the features to interaction space to learn the relationship between ship and background. The global reasoning module (GRM) based on global relational inference layers can better extract the instance segmentation results of ships. A mask assisted ship detection module (MASDM) is behind the two branches. The MASDM can improve detection results by interacting with the outputs of the two branches. In addition, a strategy is designed to extract the mask of SAR ships, which enables ISASDNet to perform object detection training and instance segmentation training at the same time. Experiments carried out two different datasets demonstrated the superiority of ISASDNet over other networks.

Synthetic aperture radar (SAR) image classification is a fundamental research in the interpretation of SAR images. The previous methods are unilaterally based on statistical features or spatial features, which cannot capture features with complete SAR image characteristics and unavoidably limits the performance for classification. In this article, novel sample weighting and class adversarial training strategies are proposed to fuse complementary SAR characteristics. Based on these, a distribution and structure match auxiliary classifier generative adversarial network (DSM-ACGAN) is constructed for high-quality discriminative feature learning. Particularly, the characteristics of statistical distribution and spatial structure are jointly considered in class adversarial training of DSM-ACGAN. On the one hand, DSM-ACGAN sets the true SAR image characteristics as goals for the generator to learn generative models of each category. On the other hand, and more importantly, it guides the discriminator to simultaneously capture the desired statistical and structural features. Through the class adversarial processing, the discriminative feature learning progressively improves and contributes to classification. Additionally, class-balanced and plausible samples can be generated. Experimental results on three broad SAR images from different satellites confirm the effectiveness of class adversarial training and the superiority of discriminative feature learning in DSM-ACGAN. Visual performance and quantitative metrics also show the state-of-the-art performance of the novel model.

Convolutional neural network (CNN)-based research has been successfully applied in remote sensing image classification due to its powerful feature representation ability. However, these high-capacity networks bring heavy inference costs and are easily overparameterized, especially for the deep CNNs pretrained on natural image datasets. Network pruning is regarded as a prevalent approach for compressing networks, but most existing research ignores model interpretability while formulating pruning criterion. To address these issues, a network pruning method for remote sensing image classification based on interpretable CNNs is proposed. More specifically, an original interpretable CNN with a predefined pruning ratio is trained at first. The filters, namely channels in the high convolutional layer, are able to learn specific semantic meanings in proportion to the predefined pruning ratio. The filters without interpretability are supposed to be removed. As for other convolutional layers, a sensitivity function is designed to assess the risk of pruning channels for each layer, and furthermore, the pruning ratio for each layer is corrected adaptively. The pruning method based on the proposed sensitivity function is effective and requires little computational costs to search abandoned channels without damaging classification performance. To demonstrate the effectiveness, the proposed method is implemented on different scales of modern CNN models, including VGG-VD and AlexNet. The experimental results, obtained on the UC Merced dataset and NWPU-RESISC45 dataset, prove that our method significantly reduces the inference costs and improves the interpretability of networks.

Synthetic aperture radar (SAR) image classification is a fundamental process for SAR image understanding and interpretation. The traditional SAR classification methods extract shallow and handcrafted features, which cannot subtly depict the abundant modal information in high resolution SAR image. Inspired by deep learning, an effective feature learning tool, a novel method called patch-sorted deep neural network (PSDNN) to implement unsupervised discriminative feature learning is proposed. First, the randomly selected patches are measured and sorted by the meticulously designed patch-sorted strategy, which adopts instance-based prototypes learning. Then the sorted patches are delivered to a well-designed dual-sparse autoencoder to obtain desired weights in each layer. Convolutional neural network is followed to extract high-level spatial and structural features. At last, the features are fed to a linear support vector machine to generate predicted labels. The experimental results in three broad SAR images of different satellites confirm the effectiveness and generalization of our method. Compared with three traditional feature descriptors and four unsupervised deep feature descriptors, the features learned in PSDNN appear powerful discrimination and the PSDNN achieves desired classification accuracy and a good visual appearance.

Land cover classification is an important application for polarimetric synthetic aperture radar (PolSAR) image interpretation. The classification performance of a promising parametric feature and classifier learning-based algorithm is limited when the amounts of pixels from different classes vary greatly. PolSAR data from minority classes is difficult to recognize correctly owing to a strong learning bias toward the majority classes, resulting in under-performing features for minority classes. To address this issue, a cost-sensitive latent space learning network based on the feature and classifier learning framework is proposed to reduce the learning bias for supporting the classification of imbalanced data in PolSAR images. First, a new cost-sensitive method is developed by adaptively computing the cost coefficient from predicted labels in the optimization process. Thus, the imbalanced distribution of PolSAR data can be obtained for both the labeled and unlabeled pixels rather than a predefined misclassifying matrix for labeled pixels. Second, latent space learning is used as an auxiliary task to assist the main task of classifier learning. By weighting the distance between the learned feature and the basis of the latent space with a different cost-sensitive coefficient, pixels in minority and majority classes are promoted to be more separable. Thus, the strong bias to majority classes is reduced from both the feature learning and classification process. Finally, the proposed method is studied through experiments on three different PolSAR images with several existing state-of-the-art methods. The experiments validate the effectiveness of the proposed method for balanced and imbalanced PolSAR land cover classification.