Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image target detection method based on weak supervised learning

A target detection and weak supervision technology, applied in the field of neural networks, can solve problems such as over-dependence and weak supervision learning, and achieve the effect of ensuring accuracy

Pending Publication Date: 2019-10-18
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to: in order to solve the technical problem that the existing image target detection method based on deep learning is overly dependent on manual labeling, a deep convolutional neural network model based on multi-scale feature maps is designed to extract the category heat map of the generated image, based on The category heat map output by the model realizes the image target detection task, and proposes an image target detection method based on weakly supervised learning

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
  • Image target detection method based on weak supervised learning
  • Image target detection method based on weak supervised learning
  • Image target detection method based on weak supervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0047] This embodiment is aimed at detecting a pair of real scene images. The training of the model is carried out using the public data set VOCPascal. The pre-training backbone network module is carried out using the classification network Inception-ResNet-v2 trained on the public data set ImageNet. The target category (classification result ) for airplanes, bicycles, birds, ships, bottles, buses, cars, cats, chairs, cows, dining tables, dogs, horses, motorcycles, humans, potted plants, sheep, sofas, trains, and displays Wait.

[0048] A method for image target detection based on weakly supervise...

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 image target detection method based on weak supervised learning, and belongs to the technical field of machine vision. The method comprises the following steps: firstly, collecting an image data set, and training a constructed deep convolutional neural network model based on a multi-scale feature map by adopting a multi-example learning method; inputting an actual image,and extracting a category thermodynamic diagram of the actual image through the deep convolutional neural network model; and finally, outputting a bounding box of a target in the category thermodynamic diagram by adopting a binarization image connected region analysis method to obtain a target detection result. According to the method, an image target detection task is realized based on a weak supervised learning method. The target detection task can be completed only by using the image-level classification annotation information in annotation in convolutional neural network model training, which is different from the target bounding box annotation information required in the prior art, so that the work of manually annotating the target in the image is greatly reduced, and the completionof the image target detection task has more economic benefits.

Description

technical field [0001] The invention belongs to the technical field of neural networks, and in particular relates to an image target detection method based on weakly supervised learning. Background technique [0002] With the increasing application of deep learning in computer vision tasks, the current deep neural network models perform well in tasks such as image classification, object detection, and semantic segmentation. However, training models in supervised learning requires a large amount of manual labeling information. Information, especially position-related annotation, often consumes a lot of manpower and material resources, so weakly supervised learning methods that rely less on annotation information have become a research hotspot. Weakly supervised learning is a method of machine learning. Different from supervised learning models that require one-to-one correspondence between labels and model outputs, weakly supervised learning relies on labeling information tha...

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): G06T7/00G06K9/46G06K9/62G06N3/04
CPCG06T7/0002G06V10/462G06N3/045G06F18/2415
Inventor 屈鸿张云龙杨昀欣刘永胜季江舟
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
Eureka Blog
Learn More
PatSnap group products