公开(公告)号：US20240071056A1

公开(公告)日：2024-02-29

申请号：US18452780

申请日：2023-08-21

Applicant: Autodesk, Inc.

Inventor： Junxiang Huang ,  Alexander Huang ,  Beatriz Chinelato Guerra ,  Yen-Yun Yu

IPC: G06V10/774 ,  G06V10/764

CPC classification number: G06V10/7753 ,  G06V10/764

Abstract: A method and system provide for augmenting a photograph. An unlabeled photograph is obtained. A weakly augmented photograph and a strongly augmented photograph are obtained from the unlabeled photograph based on different types of data augmentation methods. The weakly augmented photograph is processed through a model to generate multiple weakly augmented photograph class predictions (with assigned probabilities). The multiple weakly augmented photograph class predictions are converted into positive pseudo-labels (indicating a presence of a class) or negative pseudo-labels (indicating absence of a class) using different fixed percentile thresholds. The strongly augmented photograph is processed through the model to generate a strongly augmented photograph class prediction. The model is trained to make the strongly augmented photograph label prediction match the positive pseudo-label via a cross-entropy loss. The trained model is then utilized to label the unlabeled photograph with multiple labels.