Sony patents vision model that adapts to multiple image tasks
Sony describes a computer system that uses a fixed image recognition core, known as a vision transformer, paired with a flexible adapter. This adapter learns to work with different task-specific components, allowing one core model to handle various visual jobs without retraining the entire system.
In the filing’s own words
Circuitry comprising a vision foundation model comprises a backbone, comprising a frozen pre-trained vision transformer ‘ViT’, and a trainable adapter configured to interact with tokens of the ViT for successive blocks of the ViT, by use of an injector and extractor; the trainable adapter is configured to generate an output for the backbone for passing as input to a decoder, and the trainable adapter is trained in conjunction with training a plurality of different decoders comprising a first set of decoders, respectively coupled to the backbone for respective tasks, to produce the completed vision foundation model based on multi-task learning.
What exactly they claim (claim 1)
1. Circuitry comprising a vision foundation model, comprising: a backbone, comprising: a frozen pre-trained vision transformer ‘ViT’; and a trainable adapter configured to interact with tokens of the ViT for successive interaction blocks of the ViT, by use of an injector and extractor; the trainable adapter configured to generate an output for the backbone for passing as input to a decoder; and wherein the trainable adapter is trained in conjunction with training a plurality of different decoders comprising a first set of decoders, respectively coupled to the backbone for respective tasks, to produce the completed vision foundation model based on multi-task learning.
Facts
- Company
- Sony (Sony Group Corporation)
- Official title
- VISION FOUNDATION MODEL AND METHOD
- Publication number
- US20260301395A1
- Application number
- 19095939
- Filed
- Mar 31, 2025
- Published
- Oct 1, 2026
- Inventors
- 10
- Claims
- 17
Classified under
G06V 10/82 Physics & computingG06V 10/96 Physics & computingMore from Sony in AI & software
- Sony patents AI that plays video games in your style Oct 6, 2026
- Sony patents AI that swaps game visuals for accessibility formats Sep 17, 2026
- Sony patents AI that changes game characters based on your play Oct 1, 2026
- Sony patents method to turn 2D videos into high-detail 3D animations Oct 15, 2026
- Sony patents AI bots that mimic your friends' gaming styles Sep 8, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.