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

Neural component searching method for generating image super-resolution network

A technology for image generation and search methods, applied in the field of neural component search, can solve problems such as network structure and loss function differences, large search space, long search time, etc., to speed up search time, expand flexibility, and reduce prior knowledge Introduced effects

Pending Publication Date: 2021-08-24
SOUTHEAST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with manually designed networks based on experience and multiple experimental adjustments is that different networks need to be trained in different super-resolution scenarios, and the networks are different in many aspects such as structure and loss function.
However, in these neural structure search methods, the search space is limited to the network structure, and a large amount of artificial prior knowledge is still introduced in the loss function and training strategy; and most search methods use genetic algorithms, and the search space is large, resulting in long search time

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
  • Neural component searching method for generating image super-resolution network
  • Neural component searching method for generating image super-resolution network
  • Neural component searching method for generating image super-resolution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0060] refer to figure 1 , the specific implementation steps of the neural component search method for generating an image super-resolution network proposed by the present invention are as follows.

[0061] Step S1: Design the search space The search space is a hypergraph to be searched, including search possible network nodes, connection paths, loss functions 144-147, and color space. The order of different network nodes has a great influence on the results. For example, the order of convolutional layer, activation layer, and normalization layer is usually fixed, and too free search space will greatly increase the difficulty of neural component search methods. , so ...

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

The invention discloses a neural component searching method for generating an image super-resolution network, and the method can search the image super-resolution network under different computing power limits, and the size of the network is scalable. According to the method, besides a neural network structure, color space, loss function composition and other neural components influencing neural network training and reasoning performance can be searched. According to the method, a weight sharing strategy is used at the same time, hypergraph weights constructed in all search spaces can be inherited by the searched sub-graphs, and the search time is greatly shortened. Aiming at image super-resolution reconstruction application, a simple hypergraph is constructed, and slow, general and fast image super-resolution networks are searched. In addition, the method is not only suitable for the field of image super-resolution networks, but also can be used as a general framework, and neural networks of other applications can be searched by using the proposed extension component search method by changing the search space.

Description

technical field [0001] The invention belongs to the technical field of image super-resolution, and in particular relates to a neural component search method for generating an image super-resolution network. Background technique [0002] The current image super-resolution reconstruction methods can be divided into interpolation-based methods and learning-based methods. Interpolation-based methods can use parametric methods, such as bicubic interpolation; non-parametric regression methods such as edge-directed interpolation, normalized convolution, bilateral filtering, etc. can be used to upsample the scale of the image. However, interpolation-based image super-resolution reconstruction methods perform better in smooth regions (low frequencies) and poorer in edge regions (high frequencies), because they are prone to edge blurring and jagged artifacts. [0003] Learning-based image super-resolution reconstruction methods have some good reconstruction results, but most learning...

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): G06N3/04G06N3/08G06T3/40G06K9/46G06K9/62
CPCG06N3/08G06T3/4053G06V10/462G06N3/045G06F18/253G06F18/214
Inventor 莫凌飞管旭辰
Owner SOUTHEAST UNIV
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