公开(公告)号：US20240062525A1

公开(公告)日：2024-02-22

申请号：US18270764

申请日：2021-12-03

Applicant: NEC Corporation

Inventor： Tsenjung TAI ,  Masato TODA ,  Eiji KANEKO ,  Kazutoshi SAGI

IPC: G06V10/774 ,  G06V10/764 ,  G06V10/77 ,  G06V10/776

CPC classification number: G06V10/774 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/776 ,  G06V10/82

Abstract: To provide an efficient training process even in a case where training images having a limited variation of shooting angles are available.
Solution to Problem
A training apparatus (10) comprises: feature extraction section (11) for extracting source domain feature values from input source domain image data and for extracting target domain feature values from input target domain image data; angle conversion section (12) for generating converted source domain feature values by converting the source domain feature values as if the converted source domain feature values are extracted from source domain image data having different angles from the input source domain image data, and generating converted target domain feature values by converting the target domain feature values as if the converted target domain feature values are extracted from target domain image data having different angles from the input target domain image data; class prediction section(13) for predicting source domain class prediction values from the source domain feature values and the converted source domain feature values, and predicting target domain class prediction values from the target domain feature values and the converted target domain feature values; and updating section (14) for updating at least one of (i) the feature extraction section, (ii) the angle conversion section, and (iii) the class prediction section.

公开(公告)号：US20250022164A1

公开(公告)日：2025-01-16

申请号：US18712816

申请日：2021-11-30

Applicant: NEC Corporation

Inventor： Tsenjung TAI ,  Masato TODA

IPC: G06T7/73 ,  G06V10/774

Abstract: The feature extraction section extracts source domain structural features from input source domain image data and, extracting target domain structural features from input target domain image data. The rigid transformation section generates transformed structural features by rigid transforming the structural features with reference to conversion parameters. The relighting section generates new view features with reference to the transformed structural features and the conversion parameters in a way that new view features approximate the structural features which are extracted from input image data at the views indicated by the conversion parameters. The class prediction section predicts source domain class predictions from the source domain structural features and the source domain new view features, and predicting target domain class predictions from the target domain structural features and the target domain new view features. The updating section updates at least one of the feature extraction section, the relighting extraction section, and the class prediction extraction section.