18451878. GENERATING A TEST DIFFUSION MODEL (NATIONAL TSING HUA UNIVERSITY)
Contents
GENERATING A TEST DIFFUSION MODEL
Organization Name
Inventor(s)
Pin-Yu Chen of White Plains NY (US)
I-Hsin Chung of Chappaqua NY (US)
Chuang Gan of Cambridge MA (US)
Sheng-Yen Chou of Tainan City (TW)
GENERATING A TEST DIFFUSION MODEL
This abstract first appeared for US patent application 18451878 titled 'GENERATING A TEST DIFFUSION MODEL
Original Abstract Submitted
Techniques regarding generating a synthetic dataset of objects are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can include a defining component that can define a tractable forward process associated with a diffusion model, with defining the tractable forward process including inputting noise to compromise training data, resulting in compromised training data. The computer executable components can further include a training component that, using the compromised training data, trains the diffusion model to reverse process the tractable forward process, wherein the training results in a compromised diffusion model.
