Jump to content

18210535. Learning to Personalize Vision-Language Models through Meta-Personalization (Adobe Inc.)

From WikiPatents

Learning to Personalize Vision-Language Models through Meta-Personalization

Organization Name

Adobe Inc.

Inventor(s)

Simon Jenni of Hägendorf (CH)

Fabian David Caba Heilbron of San Jose CA (US)

Chun-Hsiao Yeh of Emeryville CA (US)

Bryan Russell of San Francisco CA (US)

Josef Sivic of Prague (CZ)

Learning to Personalize Vision-Language Models through Meta-Personalization

This abstract first appeared for US patent application 18210535 titled 'Learning to Personalize Vision-Language Models through Meta-Personalization



Original Abstract Submitted

Techniques for learning to personalize vision-language models through meta-personalization are described. In one embodiment, one or more processing devices lock a pre-trained vision-language model (VLM) during a training phase. The processing devices train the pre-trained VLM to augment a text encoder of the pre-trained VLM with a set of general named video instances to form a meta-personalized VLM, the meta-personalized VLM to include global category features. The processing devices test the meta-personalized VLM to adapt the text encoder with a set of personal named video instances to form a personal VLM, the personal VLM comprising the global category features personalized with a set of personal instance weights to form a personal instance token associated with the user. Other embodiments are described and claimed.

(Ad) Transform your business with AI in minutes, not months

Custom AI strategy tailored to your specific industry needs
Step-by-step implementation with measurable ROI
5-minute setup that requires zero technical skills
Get your AI playbook

Trusted by 1,000+ companies worldwide

Cookies help us deliver our services. By using our services, you agree to our use of cookies.