公开(公告)号：US11960568B2

公开(公告)日：2024-04-16

申请号：US17519604

申请日：2021-11-05

Applicant: University of Electronic Science and Technology of China

Inventor： Xing Xu ,  Yangye Fu ,  Yang Yang ,  Jie Shao ,  Zheng Wang

IPC: G06K9/62 ,  G06F18/213 ,  G06F18/214 ,  G06F18/241 ,  G06N3/045 ,  G06N3/088

CPC classification number: G06F18/214 ,  G06F18/213 ,  G06F18/241 ,  G06N3/045 ,  G06N3/088

Abstract: A multi-source domain adaptation model by aligning partial features includes a general feature extraction module, a feature selection module for partial feature extraction with the dedicated loss function, three partial feature alignment losses, and two classifiers for adversarial training, where the three partial feature alignment losses include an intra-class partial feature alignment loss, an inter-domain partial feature alignment loss, and an inter-class partial feature alignment loss. With the partial features extracted by the general feature extraction module and the feature selection module following three different partial feature alignment losses, the model is capable of clustering the samples from the identical categories and isolating samples from distinct classes.