Learning method, learning device with multi-feeding layers and testing method, testing device using the same

Abstract

A learning method for a CNN (Convolutional Neural Network) capable of encoding at least one training image with multiple feeding layers, wherein the CNN includes a 1st to an n-th convolutional layers, which respectively generate a 1st to an n-th main feature maps by applying convolution operations to the training image, and a 1st to an h-th feeding layers respectively corresponding to h convolutional layers (1≤h≤(n-1)) is provided. The learning method includes steps of: a learning device instructing the convolutional layers to generate the 1st to the n-th main feature maps, wherein the learning device instructs a k-th convolutional layer to acquire a (k−1)-th main feature map and an m-th sub feature map, and to generate a k-th main feature map by applying the convolution operations to the (k−1)-th integrated feature map generated by integrating the (k−1)-th main feature map and the m-th sub feature map.

Description

FIELD OF THE INVENTION[0001]The present invention relates to a learning method and a learning device with one or more multi-feeding layers, and a testing method and a testing device using the same; and more particularly, to the learning method for a CNN (Convolutional Neural Network) capable of encoding at least one training image with one or more multiple feeding layers, wherein the CNN includes a 1st to an n-th convolutional layers, which respectively generate a 1st to an n-th main feature maps by applying one or more convolution operations to the training image, and a 1st to an h-th feeding layers respectively corresponding to h convolutional layers among the n convolutional layers, and wherein the h is an integer from 1 to (n-1), including steps of: (a) a learning device acquiring the training image; and (b) the learning device instructing each of the convolutional layers to apply the convolution operations to the training image or a main feature map from its previous convolutio...

AI Technical Summary

Benefits of technology

The present invention provides a method to preserve detailed information of an input image even after consecutive convolution operations are applied to it through a CNN device.

Problems solved by technology

For example, computers cannot distinguish dogs and cats from photographs alone.

Such conventional CNN operation has a problem of, once the input image is fed, losing detailed information of the input image while the feature maps are generated through the multiple convolutional layers.

Images