Patent · US Active

Text-to-visual machine learning embedding techniques

US11775578B2 · kind B2 · utility

1Cited by

4References

18Claims

0Family size

Assignee

Adobe Inc. · US

Inventors

Pranav Vineet Aggarwal · San Jose, US
Zhe Lin · Fremont, US
Baldo Faieta · San Francisco, US
Saeid Motiian · San Francisco, US

Key dates

Filing date	Aug 10, 2021
Grant date	Oct 3, 2023
Priority date	—
Expiry date	Aug 10, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06F3/0482
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding.

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