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

Feature graph up-sampling method, terminal and storage medium

A storage medium and feature map technology, applied in the field of image processing, can solve the problem of lack of feature semantic information, and achieve the effect of improving performance

Pending Publication Date: 2021-03-05
PENG CHENG LAB
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above-mentioned defects of the prior art, the present invention provides a feature map upsampling method, a terminal and a storage medium, aiming to solve the problem caused by the overall processing of the initial feature map in the process of upsampling the feature map in the prior art. The problem of insufficient semantic information

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
  • Feature graph up-sampling method, terminal and storage medium
  • Feature graph up-sampling method, terminal and storage medium
  • Feature graph up-sampling method, terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] The feature map up-sampling method provided by the present invention may be applied in a terminal, and the terminal may perform up-sampling of a feature map through the feature map up-sampling method provided by the present invention. Terminals can be, but are not limited to, various computers, mobile phones, tablet computers, vehicle-mounted computers, and portable wearable devices.

[0035] Such as figure 1 As shown, in an embodiment of the sampling method on the feature map, the steps are:

[0036] S100. Obtain a feature map to be processed, input the feature map to be processed into a pre-trained first neural network, and obtain multiple intermediate feature maps through the first neural network.

[0037] Specifically, the feature map upsampling method provided in this embodiment can be implemented as a part of the image processing task through the upsampling module in the neural network that performs the image processing task. The image processing task includes bu...

Embodiment 2

[0076] Based on the above embodiments, the present invention also provides a corresponding terminal, such as Figure 4 As shown, the terminal includes a processor 10 and a memory 20 . Understandably, Figure 4 Only some components of the terminal are shown, but it should be understood that implementation of all illustrated components is not required, and more or fewer components may be implemented instead.

[0077] The storage 20 may be an internal storage unit of the terminal in some embodiments, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk equipped on the terminal, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD ) card, flash memory card (Flash Card), etc. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application sof...

Embodiment 3

[0080] The present invention also provides a storage medium, wherein one or more programs are stored, and the one or more programs can be executed by one or more processors, so as to realize the steps of the feature map upsampling method described above.

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 feature map up-sampling method, a terminal and a storage medium, and the method comprises the steps of segmenting a to-be-processed feature map in a channel dimension, carrying out the feature map processing of all feature maps with the number of channels being less than the number of channels of the to-be-processed feature map, and then carrying out the aggregation to complete the up-sampling, so that the features on each channel of the to-be-processed feature map are independently processed, the features with richer semantics can be extracted, and the image processing performance is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a feature map upsampling method, a terminal and a storage medium. Background technique [0002] Many image processing methods based on deep learning need to perform feature map upsampling operations, such as image super-resolution, etc. Most of the upsampling modules in the existing neural network perform further feature extraction and other processing on the input feature map before using sub-pixel The convolution method completes the final upsampling operation, but this way of directly processing the initial feature map as a whole limits the semantic information of the feature, which in turn limits the performance of image processing. [0003] Therefore, the prior art still needs to be improved and improved. Contents of the invention [0004] Aiming at the above-mentioned defects of the prior art, the present invention provides a feature map upsampling metho...

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
IPC IPC(8): G06T7/10
CPCG06T2207/20081G06T2207/20084G06T7/10
Inventor 查华李伟超汪漪戴涛欧阳豪键
Owner PENG CHENG LAB
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More