Sharif Digital Repository

Machine learning algorithms often suffer from good generalization in testing domains especially when the training (source) and test (target) domains do not have similar distributions. To address this problem, several domain adaptation techniques have been proposed to improve the performance of the learning algorithms when they face accuracy degradation caused by the domain shift problem. In this paper, we focus on the non-homogeneous distributed target domains and propose a new latent subdomain discovery model to divide the target domain into subdomains while adapting them. It is expected that applying adaptation on subdomains increase the rate of detection in comparing with the situation... 

In this paper, we propose a novel approach for handling the occlusion problem in pedestrian detection through optical principles. Our proposed framework is based on a popular three-dimensional imaging technique in optics, named integral imaging, in which multiple viewpoint images captured from a three-dimensional scene are used to extract range information of the scene. The proposed approach effectively reconstructs an unobstructed view of heavily occluded pedestrians simultaneously containing range information. The range information provided by our method can be used for foreground extraction and the reconstruction output can be used in various applications, such as people detection and...