公开(公告)号：US20170140253A1

公开(公告)日：2017-05-18

申请号：US15179403

申请日：2016-06-10

Applicant: Xerox Corporation

Inventor： Safwan Wshah ,  Beilei Xu ,  Orhan Bulan ,  Jayant Kumar ,  Peter Paul

IPC: G06K9/62 ,  G06K9/46 ,  G06N3/08

CPC classification number: G06N3/08 ,  G06K9/00771 ,  G06K9/00785 ,  G06K9/4628 ,  G06K9/629 ,  G06K2209/23 ,  G06N3/0454

Abstract: A method and system for domain adaptation based on multi-layer fusion in a convolutional neural network architecture for feature extraction and a two-step training and fine-tuning scheme. The architecture concatenates features extracted at different depths of the network to form a fully connected layer before the classification step. First, the network is trained with a large set of images from a source domain as a feature extractor. Second, for each new domain (including the source domain), the classification step is fine-tuned with images collected from the corresponding site. The features from different depths are concatenated with and fine-tuned with weights adjusted for a specific task. The architecture is used for classifying high occupancy vehicle images.