公开(公告)号：US20180144209A1

公开(公告)日：2018-05-24

申请号：US15378039

申请日：2016-12-14

Applicant: Lunit Inc.

Inventor： Hyo Eun KIM ,  Sang Heum HWANG

IPC: G06K9/46 ,  G06T7/00 ,  G06N3/08 ,  G06N3/04 ,  G06F19/00

CPC classification number: G06K9/4671 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/0012 ,  G06T2207/10004 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30096 ,  G16H50/20

Abstract: Provided are an object recognition method and apparatus which determine an object of interest included in a recognition target image using a trained machine learning model and determine an area in which the object of interest is located in the recognition target image. The object recognition method based on weakly supervised learning, performed by an object recognition apparatus, includes extracting a plurality of feature maps from a training target image given classification results of objects of interest, generating an activation map for each of the objects of interest by accumulating the feature maps, calculating a representative value of each of the objects of interest by aggregating activation values included in a corresponding activation map, determining an error by comparing classification results determined using the representative value of each of the objects of interest with the given classification results and updating a CNN-based object recognition model by back-propagating the error.

公开(公告)号：US20180060722A1

公开(公告)日：2018-03-01

申请号：US15378001

申请日：2016-12-13

Applicant: Lunit Inc.

Inventor： Sang Heum HWANG ,  Hyo Eun KIM

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/0454 ,  G06N3/084

Abstract: Provided are a machine learning method based on weakly supervised learning includes extracting feature maps about a dataset given a first type of information and not given a second type of information by using a convolutional neural network (CNN), updating the CNN by back-propagating a first error value calculated as a result of performing a task corresponding to the first type of information by using a first model, and updating the CNN by back-propagating a second error value calculated as a result of performing the task corresponding to the first type of information by using a second model different from the first model, wherein the second type of information is extracted when the task corresponding to the first type of information is performed using the second model.