Unlock instant, AI-driven research and patent intelligence for your innovation.

Specific scenario generation method with semantic control being fused

A specific, scenario-based technology applied in the field of machine learning algorithms to improve work efficiency, broad application prospects, and save labor and resources

Active Publication Date: 2018-09-21
ZHENGZHOU UNIV
View PDF7 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently no model that can directly realize the generation of different specific scenarios through semantic control.

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
  • Specific scenario generation method with semantic control being fused
  • Specific scenario generation method with semantic control being fused
  • Specific scenario generation method with semantic control being fused

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The technical solutions of the present invention will be described in further detail below through specific implementation methods.

[0024] like figure 1 and figure 2 As shown, a specific scene generation method that integrates semantic control includes the following steps:

[0025] Step 1. Crawling a number of item images and a plurality of different specific scene images containing the item from the shopping website;

[0026] Step 2. Make different attribute labels according to the characteristics of the specific scene in the specific scene picture. The label is a semantic label in binary form; after the specific scene picture is cut and processed, a training sample is obtained. The training sample includes the item map and corresponds to the item map. A specific scene graph containing the item and a label describing the scene;

[0027] Step 3. Construct a conditional generative confrontation network composed of a discriminator and a generator;

[0028] Step 4. ...

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 provides a specific scenario generation method with semantic control being fused. The method comprises the following steps: selecting a plurality of article images and a plurality of different specific scenario images comprising the article; making different attribute labels according to characteristics of specific scenarios in the specific scenario images, and carrying out cutting processing on the specific scenario images to obtain training samples; constructing a conditional generative adversarial network formed by a discriminator and a generator; serving the article images and the labels as input, and inputting the article images and the labels into the generator to generate a specific scenario image described by the labels; serving the specific scenario image comprisingthe article as a target scenario image, inputting the specific scenario image described by the labels and generated by the generator, the target scenario image, the article images and the labels intothe discriminator, and carrying out model training by the discriminator through the conditional generative adversarial network; and inputting a same type of article image to be processed and the desired scenario into the trained model in the form of label to obtain a corresponding scenario image.

Description

technical field [0001] The invention belongs to the field of machine learning algorithms, and in particular relates to a method for generating a specific scene fused with semantic control. Background technique [0002] Specific scene generation with semantic control refers to allowing a computer to generate a scene described in a language through semantic control. Being able to truly describe the world has always been the pursuit of human beings. The birth of painting stems from the needs of human beings to describe the world, and the pursuit of perfection has made art. The invention of the camera made it easy for humans to record the world. After the advent of the computer, humans began to let the computer describe the real world by itself, and many generative algorithms were born. Traditional generation algorithms include gradient direction histogram, scale-invariant feature transformation, etc. These algorithms use the method of manually extracting features and combining...

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): G06K9/62
CPCG06F18/214G06F18/25G06F18/29
Inventor 曹仰杰陈永霞段鹏松林楠贾丽丽
Owner ZHENGZHOU UNIV