Patent · US Active

Systems and methods for semantic segmentation

US11461644B2 · kind B2 · utility

3Cited by
22References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 13, 2019
Grant dateOct 4, 2022
Priority date
Expiry dateMar 26, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Fully-supervised semantic segmentation machine learning models are augmented by ancillary machine learning models which generate high-detail predictions from low-detail, weakly-supervised data. The combined model can be trained over both fully- and weakly-supervised data. Only the primary model is required for inference, post-training. The combined model can be made self-correcting during training by adjusting the ancillary model's output based on parameters learned over both the fully- and weakly-supervised data. The self-correction module may combine the output of the primary and ancillary models in various ways, including through linear combinations and via neural networks. The self-correction module and ancillary model may benefit from disclosed pre-training techniques.

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