Patent · US Active

Methods and systems for cross-domain few-shot classification

US12217187B2 · kind B2 · utility

0Cited by
0References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 17, 2021
Grant dateFeb 4, 2025
Priority date
Expiry dateDec 7, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/096
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and media for training deep neural networks for cross-domain few-shot classification are described. The methods comprise an encoder and a decoder of a deep neural network. The training of the autoencoder comprises two training stages. For each iteration in the first training stage, a batch of data samples from the source dataset are sampled and fed to the encoder to generate a plurality of source feature maps, then determining a first training stage loss, which updates the autoencoder's parameters. For each iteration in the second training stage, the novel dataset is split into a support set and a query set. The support set is fed to the encoder to determine a prototype for each class label. The query set is also fed to the encoder to calculate a query set metric classification loss. The query set metric classification loss updates the autoencoder's parameters.

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