Method and electronic device for recognizing object based on mask updates

An electronic device for recognizing an object, comprising:

• a communication unit configured to receive a predetermined image;
• memory in which a program for updating a mask based on a preset objective function with respect to the predetermined input image is stored;
• and
• a processor configured to generate first result information in which a foreground and background of the input image have been separated from each other, generate second result information in which results of a object recognition within the input image and a boundary portion of the object have been matched, calculate an objective function to be applied to each mask head based on the first and second result information and parameter information for the first and second result information, update all of the mask heads, and perform object recognition based on the updated mask, by executing the program stored in the memory.

A method of recognizing an object based on mask updates, the method being performed by a computer and comprising:

• receiving an image comprising a predetermined recognition target object;
• extracting a first feature map by passing the input image through a backbone network;
• extracting a second feature map by passing the first feature map through a feature pyramid network;
• updating a mask for object recognition based on a controller head corresponding to the second feature map;
• and
• performing the object recognition on the second feature map based on the updated mask,
• wherein the updating of the mask for object recognition based on the controller head corresponding to the second feature map comprises updating the mask based on an objective function for calculating first result information in which a foreground and background of the input image have been separated from each other and second result information in which results of an object recognition within the input image and a boundary portion of the object have been matched.