Fine-grained image classification method and system, computer equipment and storage medium

A classification method and fine-grained technology, applied in computer components, calculations, instruments, etc., can solve problems such as complex models, inability of models to accurately locate and distinguish areas, and affect fine-grained classification performance, so as to achieve good classification performance and good classification effect Effect

Active Publication Date: 2021-01-01
SOUTH CHINA UNIV OF TECH
View PDF9 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] (2) Some models cannot accurately locate the discrimination area, and often only cover a part of the object discrimination area
[0009] (3) Some models are complex and cannot be trained end-to-end
[0011] Therefore, the above limitations affect the performance of fine-grained classification

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
  • Fine-grained image classification method and system, computer equipment and storage medium
  • Fine-grained image classification method and system, computer equipment and storage medium
  • Fine-grained image classification method and system, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Such as figure 1 As shown, the present embodiment provides a fine-grained image classification method, which includes the following steps:

[0075] S101. Build a fine-grained image classification network.

[0076] Such as figure 2 As shown, the fine-grained image classification network built in this embodiment is a dual-branch network of attention suppression and attention enhancement. The two branches are an attention suppression branch and an attention enhancement branch, and the parameters of the two branches are shared. Facilitation; this fine-grained image classification network includes a residual network and an attention layer.

[0077] Further, the residual network adopts the ResNet-50 structure, which includes five convolutional layer groups, a global pooling layer, a fully connected layer and a softmax layer, and the five convolutional layer groups are respectively the first convolutional layer group , the second convolutional layer group, the third convol...

Embodiment 2

[0119] Such as Figure 4 As shown, this embodiment provides a fine-grained image classification system, which includes a construction unit 401, a first acquisition unit 402, a training unit 403, a second acquisition unit 404, and a prediction unit 405. The specific functions of each unit are as follows:

[0120] The building unit 401 is configured to build a fine-grained image classification network; wherein, the fine-grained image classification network is a dual-branch network of attention suppression and attention enhancement, including a residual network and an attention layer.

[0121] The first acquiring unit 402 is configured to acquire a training set; wherein, the training set consists of multiple training images.

[0122] The training unit 403 is configured to use the training set to train the fine-grained image classification network, and obtain a fine-grained image classification model by using the gradient boosted maximum and minimum cross-entropy loss functions. ...

Embodiment 3

[0127] Such as Figure 5 As shown, this embodiment provides a computer device, which may be a server, a computer, etc., and includes a processor 502 connected through a system bus 501, a memory, an input device 503, a display 504, and a network interface 505; wherein, the processing The device 502 is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 506 and an internal memory 507. The non-volatile storage medium 506 stores an operating system, computer programs and databases. The internal memory 507 is non-volatile The operating system and the computer program in the non-volatile storage medium 506 provide an environment for running. When the computer program is executed by the processor 502, the fine-grained image classification method in the above-mentioned embodiment 1 is implemented, as follows:

[0128] Build a fine-grained image classification network; wherein, the fine-grained image classification network is a dual-bra...

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 fine-grained image classification method and system, computer equipment and a storage medium. The fine-grained image classification method comprises the steps of: establishing a fine-grained image classification network which is a double-branch network for attention inhibition and attention enhancement and comprises a residual network and an attention layer; acquiring a training set, wherein the training set is composed of a plurality of training images; training the fine-grained image classification network by using the training set, and acquiring a fine-grained image classification model by using a gradient-propelled maximum value and minimum value cross entropy loss function; acquiring a to-be-classifiedimage; and inputting the to-be-classified image into the fine-grained image classification model, so that the to-be-classified image flows in the residual network and does not pass through the attention layer, and a category prediction result is obtained. The fine-grained image classification method and the system is implemented based on weak supervised learning and an attention mechanism, and the fine-grained image classification model obtained throughtraining can realize a good fine-grained image classification effect.

Description

technical field [0001] The invention relates to a fine-grained image classification method, system, computer equipment and storage medium, and belongs to the field of fine-grained image classification. Background technique [0002] Image classification tasks can be divided into two categories: coarse-grained classification and fine-grained classification. Coarse-grained classification refers to distinguishing basic categories of objects. The fine-grained classification refers to the finer division of images in the same basic category, and the correct identification of subcategories of images, such as identifying orioles and seagulls that belong to the same bird. Due to belonging to the same basic category, fine-grained images have smaller appearance differences, showing the characteristics of small inter-class differences and large intra-class differences. Due to the challenge of fine-grained image classification as well as its practicality, more and more scholars have dev...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/698G06N3/045G06F18/214
Inventor 王伟凝郭沛榕李乐敏谭燕石红霞
Owner SOUTH CHINA 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

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