公开(公告)号：US11625612B2

公开(公告)日：2023-04-11

申请号：US16779035

申请日：2020-01-31

Applicant: D-WAVE SYSTEMS INC.

Inventor： Arash Vahdat ,  Mani Ranjbar ,  Mehran Khodabandeh ,  William G. Macready ,  Zhengbing Bian

IPC: G06N3/08 ,  G06N5/02 ,  G06N5/04 ,  G06N3/088 ,  G06N5/022 ,  G06N5/045

Abstract: The domain adaptation problem is addressed by using the predictions of a trained model over both source and target domain to retain the model with the assistance of an auxiliary model and a modified objective function. Inaccuracy in the model's predictions in the target domain is treated as noise and is reduced by using a robust learning framework during retraining, enabling unsupervised training in the target domain. Applications include object detection models, where noise in retraining is reduced by explicitly representing label noise and geometry noise in the objective function and using the ancillary model to inject information about label noise.

公开(公告)号：US20200257984A1

公开(公告)日：2020-08-13

申请号：US16779035

申请日：2020-01-31

Applicant: D-WAVE SYSTEMS INC.

Inventor： Arash Vahdat ,  Mani Ranjbar ,  Mehran Khodabandeh ,  William G. Macready ,  Zhengbing Bian

IPC: G06N3/08 ,  G06N5/04 ,  G06N5/02

Abstract: The domain adaptation problem is addressed by using the predictions of a trained model over both source and target domain to retain the model with the assistance of an auxiliary model and a modified objective function. Inaccuracy in the model's predictions in the target domain is treated as noise and is reduced by using a robust learning framework during retraining, enabling unsupervised training in the target domain. Applications include object detection models, where noise in retraining is reduced by explicitly representing label noise and geometry noise in the objective function and using the ancillary model to inject information about label noise.