Change detection is one of the core issues of earth observation and has been extensively studied in recent decades. This paper presents a novel deep neural network architecture based on information transmission and attention mechanism. Existing methods rely on a simple mechanism for independently encoding bi-temporal images to obtain their representation vectors. In view of the fact that these methods do not make full use of the rich information between bi-temporal images, we introduce the information transmission module in the design of DNN structure for doing the transmission and interaction of information. In addition, we introduce the attention mechanism behind the information transmission module to give the corresponding attention weight to each temporal image feature so as to enhance the change information of the image, which noticeably improves final prediction. The proposed network is validated on real remote sensing image data sets. Both visual and quantitative analyses of the experimental results demonstrate competitiveness of the proposed method.INDEX TERMS Remote sensing image, change detection, deep neural network, information transmission, attention mechanism.
Uncertainties in design variables and problem parameters are often inevitable in multi-objective optimizations, and they must be considered in an optimization task if reliable Pareto optimal solutions are to be sought. Multi-objective reliability-based design optimization has been raised as a question in design for reliability, but the disadvantages of fixed evolutionary parameters, nonuniformly distributed Pareto optimal solutions and high computational cost hinder engineering applications of reliability-based design. To deal with it, this work proposes an integrated multi-objective cultural-based particle swarm algorithm to solve the double-loop reliability-based design optimization. In the inner optimization loop, the cultural space is composed of the elitism, situational and normative knowledge to adjust the parameters for swarm space, and the crowding distance ranking is introduced to update the global and local optimum and control the maximum number of solutions in elitism knowledge. The hybrid mean value method is improved to perform reliability analysis in the outer loop to suit both concave and convex types of performance functions. In addition, the car side-impact and the injection molding machine are chosen as multi-objective reliability design examples to demonstrate the effectiveness of the proposed approach. Simultaneously, results of car side-impact problem are compared with two traditional multi-objective reliability optimization algorithms, i.e., nondominated sorting genetic algorithm and crowding distance ranking-based multi-objective particle swarm optimizer, to assess the efficiency of the proposed approach. The results denote the proposed cultural-based multi-objective particle swarm optimizer is effective and feasible to solve the reliability-based design optimization problems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.