Synthetic aperture radar (SAR) image classification is a hot topic in the interpretation of SAR images. However, the absence of effective feature representation and the presence of speckle noise in SAR images make classification difficult to handle. In order to overcome these problems, a deep convolutional autoencoder (DCAE) is proposed to extract features and conduct classification automatically. The deep network is composed of eight layers: a convolutional layer to extract texture features, a scale transformation layer to aggregate neighbor information, four layers based on sparse autoencoders to optimize features and classify, and last two layers for postprocessing. Compared with hand-crafted features, the DCAE network provides an automatic method to learn discriminative features from the image. A series of filters is designed as convolutional units to comprise the gray-level cooccurrence matrix and Gabor features together. Scale transformation is conducted to reduce the influence of the noise, which integrates the correlated neighbor pixels. Sparse autoencoders seek better representation of features to match the classifier, since training labels are added to fine-tune the parameters of the networks. Morphological smoothing removes the isolated points of the classification map. The whole network is designed ingeniously, and each part has a contribution to the classification accuracy. The experiments of TerraSAR-X image demonstrate that the DCAE network can extract efficient features and perform better classification result compared with some related algorithms.

Deep learning, which represents data by a hierarchical network, has proven to be efficient in computer vision. To investigate the effect of deep features in hyperspectral image (HSI) classification, this paper focuses on how to extract and utilize deep features in HSI classification framework. First, in order to extract spectral-spatial information, an improved deep network, spatial updated deep auto-encoder (SDAE), is proposed. SDAE, which is an improved deep auto-encoder (DAE), considers sample similarity by adding a regularization term in the energy function, and updates features by integrating contextual information. Second, in order to deal with the small training set using deep features, a collaborative representation-based classification is applied. Moreover, in order to suppress salt-and-pepper noise and smooth the result, we compute the residual of collaborative representation of all samples as a residual matrix, which can be effectively used in a graph-cut-based spatial regularization. The proposed method inherits the advantages of deep learning and has solutions to add spatial information of HSI in the learning network. Using collaborative representation-based classification with deep features makes the proposed classifier extremely robust under a small training set. Extensive experiments demonstrate that the proposed method provides encouraging results compared with some related techniques.

Few-shot learning in image classification is developed to learn a model that aims to identify unseen classes with only few training samples for each class. Fewer training samples and new tasks of classification make many traditional classification models no longer applicable. In this paper, a novel few-shot learning method named multi-scale metric learning (MSML) is proposed to extract multi-scale features and learn the multiscale relations between samples for the classification of few-shot learning. In the proposed method, a feature pyramid structure is introduced for multi-scale feature embedding, which aims to combine high-level strong semantic features with low-level but abundant visual features. Then a multi-scale relation generation network (MRGN) is developed for hierarchical metric learning, in which high-level features are corresponding to deeper metric learning while low-level features are corresponding to lighter metric learning. Moreover, a novel loss function named intra-class and inter-class relation loss (IIRL) is proposed to optimize the proposed deep network, which aims to strengthen the correlation between homogeneous groups of samples and weaken the correlation between heterogeneous groups of samples. Experimental results on miniImageNet and tieredImageNet demonstrate that the proposed method achieves superior performance in few-shot learning problem.

The classification of a synthetic aperture radar (SAR) image is a significant yet challenging task, due to the presence of speckle noises and the absence of effective feature representation. Inspired by deep learning technology, a novel deep supervised and contractive neural network (DSCNN) for SAR image classification is proposed to overcome these problems. In order to extract spatial features, a multiscale patch-based feature extraction model that consists of gray level-gradient co-occurrence matrix, Gabor, and histogram of oriented gradient descriptors is developed to obtain primitive features from the SAR image. Then, to get discriminative representation of initial features, the DSCNN network that comprises four layers of supervised and contractive autoencoders is proposed to optimize features for classification. The supervised penalty of the DSCNN can capture the relevant information between features and labels, and the contractive restriction aims to enhance the locally invariant and robustness of the encoding representation. Consequently, the DSCNN is able to produce effective representation of sample features and provide superb predictions of the class labels. Moreover, to restrain the influence of speckle noises, a graph-cut-based spatial regularization is adopted after classification to suppress misclassified pixels and smooth the results. Experiments on three SAR data sets demonstrate that the proposed method is able to yield superior classification performance compared with some related approaches.

Change detection is an important task to identify land-cover changes between the acquisitions at different times. For synthetic aperture radar (SAR) images, inherent speckle noise of the images can lead to false changed points, which affects the change detection performance. Besides, the supervised classifier in change detection framework requires numerous training samples, which are generally obtained by manual labeling. In this paper, a novel unsupervised method named saliency-guided deep neural networks (SGDNNs) is proposed for SAR image change detection. In the proposed method, to weaken the influence of speckle noise, a salient region that probably belongs to the changed object is extracted from the difference image. To obtain pseudotraining samples automatically, hierarchical fuzzy C-means (HFCM) clustering is developed to select samples with higher probabilities to be changed and unchanged. Moreover, to enhance the discrimination of sample features, DNNs based on the nonnegative- and Fisher-constrained autoencoder are applied for final detection. Experimental results on five real SAR data sets demonstrate the effectiveness of the proposed approach.