公开(公告)号：US20170124409A1

公开(公告)日：2017-05-04

申请号：US15343017

申请日：2016-11-03

Applicant: NEC Laboratories America, Inc.

Inventor： Wongun Choi ,  Fan Yang ,  Yuanqing Lin

IPC: G06K9/00 ,  G06N3/04 ,  G06K9/66 ,  G06K9/46 ,  G06K9/42

CPC classification number: G06K9/4628 ,  G06K9/3233 ,  G06N3/0454

Abstract: A computer-implemented method for training a convolutional neural network (CNN) is presented. The method includes receiving regions of interest from an image, generating one or more convolutional layers from the image, each of the one or more convolutional layers having at least one convolutional feature within a region of interest, applying at least one cascaded rejection classifier to the regions of interest to generate a subset of the regions of interest, and applying scale dependent pooling to convolutional features within the subset to determine a likelihood of an object category.