首页|Researchers Submit Patent Application, 'Training Of A Machine Learning System Fo r Object-Level Image Synthesis With Labeled- Slot Conditioning', for Approval (US PTO 20240161234)
Researchers Submit Patent Application, 'Training Of A Machine Learning System Fo r Object-Level Image Synthesis With Labeled- Slot Conditioning', for Approval (US PTO 20240161234)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – From Washington, D.C., NewsRx journali sts report that a patent application by the inventors Bini, Massimo (Tubingen, D E); Khoreva, Anna (Stuttgart, DE), filed on November 3, 2023, was made available online on May 16, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information suppli ed by the inventors: “Image synthesis is the process of artificially generating images that contain some particular desired content. It is analogous to the inve rse of the classification problem: generating an image that contains the visual contents that are associated with a specific label. Generative adversarial netwo rks (GANs) are an architecture that can be trained to generate synthetic images.