Adversarial Reconstruction-Classification Networks for PolSAR Image Classification

Polarimetric synthetic aperture radar (PolSAR) image classification has become more and more widely used in recent years. It is well known that PolSAR image classification is a dense prediction problem. The recently proposed fully convolutional networks (FCN) model, which is very good at dealing with the dense prediction problem, has great potential in resolving the task of PolSAR image classification. Nevertheless, for FCN, there are some problems to solve in PolSAR image classification. Fortunately, Li et al. proposed the sliding window fully convolutional networks (SFCN) model to tackle the problems of FCN in PolSAR image classification. However, only when the labeled training sample is sufficient, can SFCN achieve good classification results. To address the above mentioned problem, we propose adversarial reconstruction-classification networks (ARCN), which is based on SFCN and introduces reconstruction-classification networks (RCN) and adversarial training. The merit of our method is threefold: (i) A single composite representation that encodes information for supervised image classification and unsupervised image reconstruction can be constructed; (ii) By introducing adversarial training, the higher-order inconsistencies between the true image and reconstructed image can be detected and revised. Our method can achieve impressive performance in PolSAR image classification with fewer labeled training samples. We have validated its performance by comparing it against several state-of-the-art methods. Experimental results obtained by classifying three PolSAR images demonstrate the efficiency of the proposed method.

Ensemble Learning-Based Person Re-identification with Multiple Feature Representations

As an important application in video surveillance, person reidentification enables automatic tracking of a pedestrian through different disjointed camera views. It essentially focuses on extracting or learning feature representations followed by a matching model using a distance metric. In fact, person reidentification is a difficult task because, first, no universal feature representation can perfectly identify the amount of pedestrians in the gallery obtained by a multicamera system. Although different features can be fused into a composite representation, the fusion still does not fully explore the difference, complementarity, and importance between different features. Second, a matching model always has a limited amount of training samples to learn a distance metric for matching probe images against a gallery, which certainly results in an unstable learning process and poor matching result. In this paper, we address the issues of person reidentification by the ensemble theory, which explores the importance of different feature representations, and reconcile several matching models on different feature representations to an optimal one via our proposed weighting scheme. We have carried out the simulation on two well-recognized person reidentification benchmark datasets: VIPeR and ETHZ. The experimental results demonstrate that our approach achieves state-of-the-art performance.