Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for providing integrated feature map using ensemble of multiple outputs from convolutional neural network

A technology of integrating features and feature maps, applied in the field of feature maps, can solve the problem of being unable to distinguish between dogs and cats

Active Publication Date: 2020-03-10
STRADVISION
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, a computer cannot tell a dog from a cat just from a photo

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for providing integrated feature map using ensemble of multiple outputs from convolutional neural network
  • Method and device for providing integrated feature map using ensemble of multiple outputs from convolutional neural network
  • Method and device for providing integrated feature map using ensemble of multiple outputs from convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The invention will be described in detail below with reference to the accompanying drawings showing specific embodiments in which the invention can be practiced. These examples are described in detail to enable those of ordinary skill in the art to practice the present invention. The various embodiments of the invention, although different, are not necessarily mutually exclusive. For example, the specific shape, structure and characteristics described here can be realized by other embodiments without departing from the technical idea and scope of the present invention in one embodiment. In addition, it should be understood that the position or arrangement of individual components in the disclosed embodiments can be changed without departing from the technical idea and scope of the present invention. Therefore, the following detailed description is not intended to be limited. Specifically, the scope of the present invention is the scope described in the technical soluti...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method for providing an integrated feature map by using an ensemble of a plurality of outputs from a convolutional neural network (CNN) is provided. The method includes steps of: a CNN device (a) receiving an input image and applying a plurality of modification functions to the input image to thereby generate a plurality of modified input images; (b) applying convolution operations to each of the modified input images to thereby obtain each of modified feature maps corresponding to each of the modified input images; (c) applying each of reverse transform functions, corresponding to each of the modification functions, to each of the corresponding modified feature maps, to thereby generate each of reverse transform feature maps corresponding to each of the modified feature maps; and (d) integrating at least part of the reverse transform feature maps to thereby obtain an integrated feature map.

Description

technical field [0001] The present invention relates to methods and apparatus for providing integrated feature maps from convolutional neural networks using combinations of multiple outputs. More specifically, it relates to a step characterized by comprising: (a) the CNN device receives an input image and applies a plurality of deformation functions that deform the input image to generate a plurality of deformed input images; (b) the CNN device generates a plurality of deformed input images; Applying a convolution operation to the deformed input image to obtain a step of each deformed feature map corresponding to each of the deformed input images; (c) the CNN device is respectively applied to each deformed feature map corresponding to each deformation The inverse transformation function of the function respectively generates the step of the inverse transformation feature map corresponding to the feature map of each deformation; and (d) the CNN device integrates at least a part...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G06V10/764G06V20/00
CPCG06N3/08G06N3/084G06V20/00G06N3/045G06F18/217G06F18/24133G06F18/214G06V10/82G06V10/764G06N3/0455G06N3/0464G06N3/09G06V10/454G06V10/7747G06V10/776G06N3/04
Inventor 金桂贤金镕重金寅洙金鹤京南云铉夫硕焄成明哲吕东勋柳宇宙张泰雄郑景中诸泓模赵浩辰
Owner STRADVISION
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com