Patent · US Active

Extracting gradient features from neural networks

US9792492B2 · kind B2 · utility

21Cited by
1References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 7, 2015
Grant dateOct 17, 2017
Priority date
Expiry dateJan 25, 2036

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for extracting a representation from an image includes inputting an image to a pre-trained neural network. The gradient of a loss function is computed with respect to parameters of the neural network, for the image. A gradient representation is extracted for the image based on the computed gradients, which can be used, for example, for classification or retrieval.

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