公开(公告)号：US20250054288A1

公开(公告)日：2025-02-13

申请号：US18366394

申请日：2023-08-07

Applicant: NVIDIA Corporation

Inventor： Yuan-Hong LIAO ,  David Jesus ACUNA MARRERO ,  James LUCAS ,  Rafid MAHMOOD ,  Sanja FIDLER ,  Viraj Uday PRABHU

IPC: G06V10/82 ,  G06V20/70

Abstract: Various examples relate to translating image labels from one domain (e.g., a synthetic domain) to another domain (e.g., a real-world domain) to improve model performance on real-world datasets and applications. Systems and methods are disclosed that provide an unsupervised label translator that may employ a generative adversarial network (GAN)-based approach. In contrast to conventional systems, the disclosed approach can employ a data-centric perspective that addresses systematic mismatches between datasets from different sources.