Cosine measurement supervised deep hash algorithm with balanced similarity

A hash algorithm and similarity technology, applied in the field of cosine metric supervised deep hash algorithm, can solve the problems of small global gradient, slow model convergence, and reduced retrieval performance, and achieve the effect of reducing quantization errors and imbalance problems.

Pending Publication Date: 2021-03-12
BEIJING UNIV OF TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although an easy pair contributes less to the global gradient than a hard pair, the total contribution of a large number of easy pairs is cumulative and may exceed that of a small number of hard pairs
This phenomenon makes the model converge slowly, may fall into local optimum, and even reduce the retrieval performance to a certain extent

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
  • Cosine measurement supervised deep hash algorithm with balanced similarity
  • Cosine measurement supervised deep hash algorithm with balanced similarity
  • Cosine measurement supervised deep hash algorithm with balanced similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The invention proposes a cosine metric supervised deep hashing algorithm with balanced similarity. Overall structure of the present invention is as figure 1 shown. The embodiment of the present invention carries out emulation under win10 and matlab environment. The concrete realization steps of this invention are as follows:

[0017] Step 1: Establish the similarity matrix S of the image pair and image preprocessing, regard the labeled images of the same category in the image training set as similar, and regard the images of completely different categories as dissimilar. Image preprocessing follows the unified settings of the current deep hash algorithm.

[0018] Step 2: Establish a deep network model. In this embodiment, AlexNet is used to remove the last classification layer and add a hash layer to obtain a hash code. The hash layer is a fully connected layer whose output dimension is the dimension of the hash code. There is no need to use the tanh activation fun...

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 a cosine measurement supervised deep hash algorithm with balanced similarity, and belongs to the field of image retrieval. The deep supervised hash has the advantages of low storage cost, high calculation efficiency and the like. However, similarity preserving, quantization error, and imbalance data are still huge challenges in deep supervised hashing. The invention provides a deep hash scheme for pairwise similarity preservation, and solves the problem. According to the method, a deep network is used as a basic model to extract features, and a hash layer is used to replace a final classification layer to enable the final classification layer to output hash codes. According to the method, a loss function is designed, semantic similarity can be effectively kept in the training process, and the problems of class imbalance, difficulty and quantitative loss are solved. When the hash code obtained by the method is used for image retrieval, the retrieval accuracy canbe effectively improved for an extremely unbalanced data set.

Description

technical field [0001] The invention relates to the field of image retrieval, and in particular relates to a cosine metric supervised deep hash algorithm with balanced similarity. Background technique [0002] With the rapid development of multimedia processing technology, large-scale image search has been widely used in our daily life. As one of the most effective technologies, hashing technology has attracted more and more attention from academia and industry due to its storage and computing advantages. It aims to map high-dimensional images to compact binary codes while preserving image correlation. In particular, deeply supervised hashing may improve retrieval performance by integrating image features and hash coding through end-to-end learning. [0003] Hash embedding is generally implemented with discrete optimization, which is a standard NP-hard problem. Deeply supervised hashing methods mostly employ continuous relaxation, replacing discrete encoding with approxim...

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
CPCG06N3/08G06N3/045G06F18/22
Inventor 毋立芳陈禹锟胡文进简萌
Owner BEIJING UNIV OF TECH
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