Image and Feature Space Based Domain Adaptation for Vehicle Detection

作     者：Ying Tian Libing Wang Hexin Gu Lin Fan 

作者机构：School of Computer Science and Software EngineeringUniversity of Science and Technology LiaoningAnshan114051China School of Mechanical Engineering and AutomationUniversity of Science and Technology LiaoningAnshan114051China Faculty of BusinessEconomics&LawThe University of QueenslandBrisbaneQLD 4072Australia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2020年第65卷第12期

页      面：2397-2412页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：: The authors received no specific funding for this study 

主　　题：Deep learning cross-domain vehicle detection 

摘      要：The application of deep learning in the field of object detection has experienced much ***,due to the domain shift problem,applying an off-the-shelf detector to another domain leads to a significant performance drop.A large number of ground truth labels are required when using another domain to train models,demanding a large amount of human and financial *** order to avoid excessive resource requirements and performance drop caused by domain shift,this paper proposes a new domain adaptive approach to cross-domain vehicle *** approach improves the cross-domain vehicle detection model from image space and feature *** employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image *** feature space,we align feature distributions between the source domain and the target domain to improve the detection *** are carried out using the method with two different datasets,proving that this technique effectively improves the accuracy of vehicle detection in the target domain.