Patent · US Active

Systems and methods for saliency-based sampling layer for neural networks

US11430084B2 · kind B2 · utility

0Cited by

7References

21Claims

0Family size

Assignees

TOYOTA RESEARCH INSTITUTE, INC. · US
Massachusetts Institute of Technology · US

Inventors

Simon A. I. Stent · Cambridge, US
Adrià Recasens · Cambridge, US
Antonio Torralba · Cambridge, US
Petr Kellnhofer · Cambridge, US
Wojciech Matusik · Lexington, US

Key dates

Filing date	Sep 5, 2018
Grant date	Aug 30, 2022
Priority date	—
Expiry date	Feb 13, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/084
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method includes receiving, with a computing device, an image, identifying one or more salient features in the image, and generating a saliency map of the image including the one or more salient features. The method further includes sampling the image based on the saliency map such that the one or more salient features are sampled at a first density of sampling and at least one portion of the image other than the one or more salient features are sampled at a second density of sampling, where the first density of sampling is greater than the second density of sampling, and storing the sampled image in a non-transitory computer readable memory.

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