Weak supervision target detection method based on image attribute learning

A target detection, weakly supervised technology, applied in neural learning methods, instruments, biological neural network models, etc.

Active Publication Date: 2021-05-28
NORTHWESTERN POLYTECHNICAL UNIV
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The target detection task requires the computer to be able to deeply understand the content of the image and extract the corresponding image features. The answer to some questions also requires the computer to master relevant common sense or specific knowledge. Therefore, many artificial intelligence technologies are involved in the target detection research, including Target classification, object recognition and natural language processing, etc., which makes the research of target detection methods have higher requirements and greater challenges in specific target recognition than image classification.

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
  • Weak supervision target detection method based on image attribute learning
  • Weak supervision target detection method based on image attribute learning
  • Weak supervision target detection method based on image attribute learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The present invention will now be further described in conjunction with the embodiments and accompanying drawings:

[0072] This method is based on a weakly supervised target detection method represented by image attributes. The model used consists of five sub-modules: image feature extraction and target proposal frame extraction, text processing and feature extraction module, pseudo ground-truth mining module, image Attribute learning and classification module, target classification and detection box regression module.

[0073] 1. Image feature extraction and target proposal box extraction module

[0074] First, use the convolutional neural network module (VGG16 or ResNet) to extract features from the original image. The result of extraction is a feature vector on the entire image, and then this feature vector is used as an input to the RPN (Region Proposal Network) network, and the target proposal frame on the entire image can be finally extracted through the RPN net...

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 relates to a weak supervision target detection method based on image attribute representation learning, and belongs to the technical field of image processing. The method sequentially comprises the steps of label text description data processing, image feature extraction and target suggestion box extraction, label text feature construction, text and image feature fusion-based pseudo ground-truth mining, image attribute learning and prediction module, target classification and target suggestion box regression. According to the method, the interpretability of target classification is improved through image attribute learning, the mined pseudo group-truth is more accurate by utilizing text feature and image feature fusion, and the detection capability of the weak supervision model is improved.

Description

technical field [0001] The invention belongs to the field of computer application, image processing, text processing, and target detection research, and in particular relates to a weakly supervised target detection method based on image attribute learning. Background technique [0002] Object Detection is a very important research field in the field of computer vision at present. Its research goal is to enable computers to recognize and classify objects in images. The specific process is to input an image to the computer, and then extract the features of the image to identify and classify the target. The target detection task requires the computer to be able to deeply understand the content of the image and extract the corresponding image features. The answer to some questions also requires the computer to master relevant common sense or specific knowledge. Therefore, many artificial intelligence technologies are involved in the target detection research, including Target c...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V2201/07G06N3/048G06N3/044G06N3/045G06F18/2415G06F18/253
Inventor 宋凌云李伟尚学群彭杨柳李建鳌俞梦真贺梦婷李战怀
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap