End-to-end weak supervision target detection method based on salient guidance

A technology of target detection and weak supervision, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of no mining and little improvement in target detection performance

Inactive Publication Date: 2017-09-26
ZHEJIANG UNIV
View PDF2 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods only use the features in the deep neural network to obtain more information in the image, so the performance of target detection is not greatly improved.

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
  • End-to-end weak supervision target detection method based on salient guidance
  • End-to-end weak supervision target detection method based on salient guidance
  • End-to-end weak supervision target detection method based on salient guidance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The present invention is further described below.

[0065] Embodiments of the present invention and its implementation process are:

[0066] (1) Collect an image I with a known image-level label, and the image-level label is y=[y 1 ,y 2 ,...,y C ], where y c Represents the label corresponding to the c-th category object in the image, the label is divided into foreground label and background label, each label attribute is foreground label or background label, y c ∈{1,-1},y c =1 means that there is an object of the cth category in the image, y c =-1 means that there is no c-th category object in the image, one label corresponds to one category object, and C is the total number of category objects;

[0067] (2) Process the image I to obtain the category-related saliency map M corresponding to each category object c , candidate target area and with each candidate target region set of adjacent superpixels;

[0068] Use the DCSM algorithm to process the image I to...

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 an end-to-end weak supervision target detection method based on salient guidance. According to the method, a deep neural network is constructed, and a salient sub-network of a target box is added on the basis of a weak supervised classifier network; meanwhile, seed target areas with related categories are selected according to the criterion of context difference by the aid of a category-related salient map trained with a weak supervision method, and the salient sub-network and a classifier sub-network are supervised and trained. Compared with existing weak supervision target detection methods, the method has the advantages that better performance is obtained, meanwhile, only training of image-grade labels is required, and the workload of training data labeling is reduced.

Description

technical field [0001] The invention relates to an image target detection method, in particular to an end-to-end weakly supervised target detection method based on saliency guidance. Background technique [0002] Object detection aims to mark the objects and their categories in the image with rectangular boxes. Traditional machine learning-based object detection methods generally belong to the supervised learning method, which requires training data with the true value of the rectangular box. However, in big data scenarios, marking a large number of rectangular boxes requires a lot of manpower, which limits the application of supervised learning methods on large-scale data sets. [0003] In order to solve the problem of expensive training data, in recent years, researchers have developed learning methods based on weakly supervised labels. Although the supervision ability of weakly supervised marks is weaker than that of supervised marks, the cost of obtaining weakly superv...

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): G06K9/62G06K9/46
CPCG06V10/462G06F18/2155G06F18/24
Inventor 赖百胜龚小谨
Owner ZHEJIANG 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