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

Multi-label image retrieval method fusing triple loss and generative adversarial network

An image retrieval, multi-label technology, applied in metadata still image retrieval, still image data retrieval, biological neural network model, etc., to achieve the effect of expanding the amount of training data and improving retrieval speed and accuracy

Active Publication Date: 2019-10-11
重庆医药数据信息科技有限公司
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the shortcomings of the existing methods, the present invention proposes a multi-label image retrieval method that integrates triplet loss and generative adversarial networks to solve the problems existing in the prior art. the above question

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
  • Multi-label image retrieval method fusing triple loss and generative adversarial network
  • Multi-label image retrieval method fusing triple loss and generative adversarial network
  • Multi-label image retrieval method fusing triple loss and generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] like figure 1 As shown, an embodiment of the present invention provides a multi-label image retrieval method that combines triplet loss and generative confrontation network, including steps S1-S6.

[0077] Step S1: Build a deep learning framework, deploy a generative adversarial network model, and the generative adversarial network model includes a deep hash coding network.

[0078] S1-1. Build the Caffe deep learning open source framework, and deploy the DCGAN model in the Caffe deep learning open source framework.

[0079] Specifically, in step S1, the present invention builds a Caffe (Convolutional Architecture for Fast Feature Embedding, convolutional architecture for fast feature embedding) deep learning framework. In this embodiment, DCGAN (Deep convolutional generative adversarial networks) network structure (for example, VGG16 can be used) is used as the image generation model. Take the original loss function of the GAN model as its loss function and optimizat...

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 multi-label image retrieval method fusing triple loss and generative adversarial network, which comprises the following steps of: establishing a deep learning framework, and deploying a generative adversarial network model; inputting the image data set into the generative adversarial network model to obtain a multi-label image and triple data; constructing a triple loss function based on the multi-label image; selecting a first image from the image data set to train the deep hash coding network so as to obtain a trained deep hash coding network; selecting a preset number of second images from the image data set, and inputting the second images into the trained deep hash coding network to obtain a hash vector database; and inputting a first image to be retrieved into the trained deep hash coding network to retrieve a second image similar to the first image. According to the invention, the generative adversarial network is used to generate the multi-label generation picture similar to the data set sample, the training data volume is expanded, and the retrieval speed and precision of the image are improved.

Description

technical field [0001] The invention relates to the field of image retrieval, in particular to a multi-label image retrieval method that integrates triplet loss and generative confrontation network. Background technique [0002] With the explosive growth of image and video data on the Internet, large-scale image retrieval tasks have received increasing attention in recent years. The main task of the image retrieval system is not only to ensure the image quality in the retrieval results, but also to ensure the efficiency of retrieval, and at the same time, it is also necessary to solve how to efficiently store massive information, so that users can have a better experience. [0003] Representing images efficiently is an important task for large-scale image retrieval. Binary hashing has gained a lot of attention due to the computational efficiency and storage efficiency of binary hash codes. Its goal is to map high-dimensional image data into the same Hamming space while mai...

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): G06K9/62G06N3/04G06N3/08G06F16/58
CPCG06N3/08G06F16/5866G06N3/045G06F18/25G06F18/214
Inventor 冯永黄嘉琪强保华尚家兴刘大江
Owner 重庆医药数据信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products