Google patents AI model design that mixes image detail levels
Google describes a method for building machine learning models by rearranging blocks of data processing in a specific, non-standard order. Instead of always moving from low to high detail, the model switches between different levels of resolution to improve accuracy while using less computer power.
In the filing’s own words
A computer-implemented method of generating scale-permuted models can generate models having improved accuracy and reduced evaluation computational requirements. The method can include defining, by a computing system including one or more computing devices, a search space including a plurality of candidate permutations of a plurality of candidate feature blocks, each of the plurality of candidate feature blocks having a respective scale. The method can include performing, by the computing system, a plurality of search iterations by a search algorithm to select a scale-permuted model from the search space, the scale-permuted model based at least in part on a candidate permutation of the plurality of candidate permutations.
What exactly they claim (claim 1)
1. A computing system, comprising: a machine-learned scale-permuted model, the machine-learned scale-permuted model comprising: a scale-permuted network generated through permutation of a plurality of feature blocks, the scale-permuted network comprising the plurality of feature blocks arranged in a scale-permuted sequence such that a resolution of the plurality of feature blocks varies nonmonotonically throughout the scale-permuted sequence; wherein the scale-permuted network comprises a sequence of blocks comprising: a first feature block in the sequence having a first resolution, a second feature block next in the sequence after the first feature block, the second feature block having a second resolution higher than the first resolution, and a third feature block next in the sequence after the second feature block, the third feature block having a third resolution lower than the second resolution and different from the first resolution; one or more processors; and one or more memory devices storing computer-readable instructions that, when implemented, cause the one or more processors to perform operations, the operations comprising: obtaining input data, the input data comprising an input tensor; providing the input data to the machine-learned scale-permuted model; and receiving, as output from the machine-learned scale-permuted model, output data.
Facts
- Company
- Google (Google LLC)
- Official title
- Scale-permuted machine learning architecture
- Patent number
- US12737689B2
- Application number
- 18784068
- Filed
- Jul 25, 2024
- Granted
- Sep 15, 2026
- Inventors
- 8
- Claims
- 20
Classified under
G06N 20/00 Physics & computingG06F 11/3495 Physics & computingG06N 3/04 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.