Unified Network Framework Research Articles

Polarimetric Synthetic Aperture Radar Image Classification Based on Double-Channel Convolution Network and Edge-Preserving Markov Random Field

Deep learning methods have gained significant popularity in the field of polarimetric synthetic aperture radar (PolSAR) image classification. These methods aim to extract high-level semantic features from the original PolSAR data to learn the polarimetric information. However, using only original data, these methods cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these limitations, we propose a novel approach that combines a new double-channel convolutional neural network (CNN) with an edge-preserving Markov random field (MRF) model for PolSAR image classification, abbreviated to “DCCNN-MRF”. Firstly, a double-channel convolution network (DCCNN) is developed to combine complex matrix data and multiple scattering features. The DCCNN consists of two subnetworks: a Wishart-based complex matrix network and a multi-feature network. The Wishart-based complex matrix network focuses on learning the statistical characteristics and channel correlation, and the multi-feature network is designed to learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of weighted features in order to enhance advantageous features and reduce redundant ones. Finally, an edge-preserving MRF model is integrated with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining an adaptive weighted neighborhood for edge pixels. Experiments were conducted on four real PolSAR datasets with different sensors and bands. The experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.

Learning a Deep CNN Denoising Approach Using Anatomical Prior Information Implemented With Attention Mechanism for Low-Dose CT Imaging on Clinical Patient Data From Multiple Anatomical Sites.

Dose reduction in computed tomography (CT) has gained considerable attention in clinical applications because it decreases radiation risks. However, a lower dose generates noise in low-dose computed tomography (LDCT) images. Previous deep learning (DL)-based works have investigated ways to improve diagnostic performance to address this ill-posed problem. However, most of them disregard the anatomical differences among different human body sites in constructing the mapping function between LDCT images and their high-resolution normal-dose CT (NDCT) counterparts. In this article, we propose a novel deep convolutional neural network (CNN) denoising approach by introducing information of the anatomical prior. Instead of designing multiple networks for each independent human body anatomical site, a unified network framework is employed to process anatomical information. The anatomical prior is represented as a pattern of weights of the features extracted from the corresponding LDCT image in an anatomical prior fusion module. To promote diversity in the contextual information, a spatial attention fusion mechanism is introduced to capture many local regions of interest in the attention fusion module. Although many network parameters are saved, the experimental results demonstrate that our method, which incorporates anatomical prior information, is effective in denoising LDCT images. Furthermore, the anatomical prior fusion module could be conveniently integrated into other DL-based methods and avails the performance improvement on multiple anatomical data.

Security synchronization protocol for IT2 stochastic fuzzy multiplex complex networks via fuzzy hybrid control

An issue regarding security synchronization is addressed for a class of interval type-2 (IT2) fuzzy stochastic multiplex complex networks with fuzzy hybrid control under deception attacks. Firstly, some complicated facts are considered in a unified network framework, such as multiplex, multiple delays, and stochastic disturbances, etc. In particular, different from the traditional hypothesis, the uncertainty is taken into consideration for the membership functions and along with the strategy of upper and lower bound and the correlative tradeoff functions to overcome this uncertainty. Secondly, malicious data are injected into channels between sensor and controller that may lead to undesired system performance. Then, based on Lyapunov stability theory and comparison principle, a novel IT2 fuzzy hybrid controller, containing a state feedback controller and a network-based impulsive controller, is designed to ensure a mean-square bounded synchronization so that the error states can converge below error thresholds. Finally, impulsive effects including both positive and negative roles are considered simultaneously in the security synchronization strategy, and the feasibility of the designed scenario is demonstrated by two numerical examples.

Deep discrete hashing with pairwise correlation learning

Hashing technology plays an important role in large-scale visual search due to its low memory and fast retrieval speed. Most existing deep hashing approaches first leverage the continuous relaxation strategy to learn continuous approximate codes, and then transform them into discrete hash codes by separating quantization operations, which results in the suboptimal problem of hash codes and ultimately affects the performance of image retrieval. To solve this problem, we propose a novel deep discrete hashing approach with pairwise labels, namely Pairwise Correlation Discrete Hashing (PCDH), to leverage the pairwise correlation of deep features and semantic supervised information to directly guide discrete hashing codes learning. Firstly, we integrate discrete hash code learning and deep features learning in a unified network framework, which can utilize the semantic supervision to guide discrete hash codes learning. Secondly, we design a novel pairwise correlation constraint to perform pairwise correlation learning of deep features. Thirdly, we develop a novel pairwise construction module to mine good pairwise samples for discrete hash codes learning. Extensive experimental results show that the proposed PCDH approach achieves superior performance over other recent state-of-the-art hashing approaches.