US 12,217,484 B2
Method of unsupervised domain adaptation in ordinal regression
Boris Chidlovskii, Meylan (FR); and Assem Sadek, Meylan (FR)
Assigned to Naver Corporation, (KR)
Filed by Naver Corporation, Seongnam-si (KR)
Filed on May 5, 2022, as Appl. No. 17/737,114.
Claims priority of provisional application 63/294,112, filed on Dec. 28, 2021.
Claims priority of provisional application 63/290,230, filed on Dec. 16, 2021.
Prior Publication US 2023/0196733 A1, Jun. 22, 2023
Int. Cl. G06V 10/77 (2022.01); G06V 10/774 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/7715 (2022.01) [G06V 10/7753 (2022.01); G06V 10/7792 (2022.01); G06V 10/7796 (2022.01); G06V 10/82 (2022.01)] 12 Claims
OG exemplary drawing
 
1. An ordinal regression unsupervised domain adaption network for jointly training of a transferable feature extractor network, an ordinal regressor network, and an order classifier network, comprising:
a source of labeled source images and unlabeled target images;
a transferable feature extractor network, operatively connected to said source of labeled source images and unlabeled target images, to output image representations, said image representations being realized by a minimax optimization procedure;
a domain discriminator network operatively connected to said transferable feature extractor network;
an ordinal regressor network operatively connected to said transferable feature extractor network; and
an order classifier network operatively connected to said transferable feature extractor network and said domain discriminator network;
said domain discriminator network being trained, using said image representations from said transferable feature extractor network, to distinguish between source images and target images;
said ordinal regressor network being trained, using a full set of source images from said transferable feature extractor network;
said order classifier network being trained, using a pair of source images from said transferable feature extractor network.