Unsupervised depth hashing method based on target detection

A target detection, unsupervised technology, applied in the direction of digital data information retrieval, special data processing applications, instruments, etc., can solve the problem of not being able to use pictures
CN110196918AInactive Publication Date: 2019-09-03BEIJING INSTITUTE OF TECHNOLOGYGY +1
7 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
BEIJING INSTITUTE OF TECHNOLOGYGY
Publication Date
2019-09-03
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to an unsupervised depth hashing method based on target detection, and belongs to the technical field of computer information retrieval and picture retrieval. The method comprises the steps of obtaining the object tags existing in the pictures by utilizing the target detection, taking the tags as pseudo tags of the pictures, and training a designed end-to-end depth hash modelbased on the pseudo tags to obtain the hash code representation of each picture in a Hamming space; evaluating the quality of the deep Hash model through the average accuracy mean value of the corresponding Hash codes in the picture retrieval task, wherein the average accuracy rate mean value is the MAP, and the unsupervised deep hash model comprises a target detection algorithm unit and a hash network unit. According to the method, the more instructive information can be obtained, the capability of a depth model can be fully utilized to learn the high-quality Hash codes with maintained similarity, and the picture retrieval is carried out in a real picture data set to obtain the best effect, namely, the MAP value is the highest.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to an unsupervised deep hashing method based on target detection, and belongs to the technical fields of computer information retrieval technology and picture retrieval technology. Background technique

[0002] With the rapid growth of image data, approximate nearest neighbor (ANN) search has received more and more attention from researchers in the field of large-scale image search. In the existing artificial neural network search technology, the hash method that preserves the similarity has the advantages of high retrieval efficiency and low storage cost. The main idea of ​​hashing methods is to convert high-dimensional data points into a set of compact binary codes while maintaining the similarity of the original data points. Since the raw data points are represented in binary codes instead of real-valued features, the time and memory overhead of searching can be greatly reduced.

[0003] At present, most of the hashing method...

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