Patent · US Active

Methods and apparatus to perform dense prediction using transformer blocks

US12380714B2 · kind B2 · utility

0Cited by
0References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 25, 2021
Grant dateAug 5, 2025
Priority date
Expiry dateMar 11, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20221
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, apparatus, systems and articles of manufacture disclosed herein perform dense prediction of an input image using transformers at an encoder stage and at a reassembly stage of an image processing system. A disclosed apparatus includes an encoder with an embedder to convert an input image to a plurality of tokens representing features extracted from the input image. The tokens are embedded with a learnable position embedding. The encoder also includes one or more transformers configured in a sequence of stages to relate the tokens to each other. The apparatus further includes a decoder that includes one or more of reassemblers to assemble the tokens into feature representations, one or more of fusion blocks to combine the feature representations to generate a final feature representation, and an output head to generate a dense prediction based on the final feature representation and based on an output task.

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