Patent · US Active

Learning to segment via cut-and-paste

US11853892B2 · kind B2 · utility

0Cited by

4References

20Claims

0Family size

Assignee

Google LLC · US

Inventors

Matthew Brown · Seattle, US
Jonathan Huang · San Carlos, US
Tal Remez · Jerusalem, IL

Key dates

Filing date	Jul 10, 2019
Grant date	Dec 26, 2023
Priority date	—
Expiry date	Aug 17, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG06T2210/12
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Example aspects of the present disclosure are directed to systems and methods that enable weakly-supervised learning of instance segmentation by applying a cut-and-paste technique to training of a generator model included in a generative adversarial network. In particular, the present disclosure provides a weakly-supervised approach to object instance segmentation. In some implementations, starting with known or predicted object bounding boxes, a generator model can learn to generate object masks by playing a game of cut-and-paste in an adversarial learning setup.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.