Patent · US Active

Learning method and learning device for adjusting parameters of CNN by using multi-scale feature maps and testing method and testing device using the same

US10007865B1 · kind B1 · utility

18Cited by
0References
30Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 16, 2017
Grant dateJun 26, 2018
Priority date
Expiry dateOct 16, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A learning method for acquiring a bounding box corresponding to an object in a training image from multi-scaled feature maps by using a CNN is provided. The learning method includes steps of: (a) allowing an N-way RPN to acquire at least two specific feature maps and allowing the N-way RPN to apply certain operations to the at least two specific feature maps; (b) allowing an N-way pooling layer to generate multiple pooled feature maps by applying pooling operations to respective areas on the at least two specific feature maps; and (c) (i) allowing a FC layer to acquire information on pixel data of the bounding box, and (ii) allowing a loss layer to acquire first comparative data, thereby adjusting at least one of parameters of the CNN by using the first comparative data during a backpropagation process.

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