Face attribute recognition method of deep neural network based on cascaded multi-task learning

A deep neural network and multi-task learning technology, which is applied in neural learning methods, biological neural network models, neural architectures, etc., can solve the problem that the difference of face attributes is not effectively utilized, and the recognition effect of face attributes cannot be optimized, etc. question

Active Publication Date: 2018-09-21
XIAMEN UNIV
View PDF3 Cites 66 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, since the differences among face attributes are not effective

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
  • Face attribute recognition method of deep neural network based on cascaded multi-task learning
  • Face attribute recognition method of deep neural network based on cascaded multi-task learning
  • Face attribute recognition method of deep neural network based on cascaded multi-task learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following examples will describe the present invention in detail with reference to the accompanying drawings. The present example is implemented on the premise of the technical solution of the present invention, and the implementation manner and specific operation process are given, but the protection scope of the present invention is not limited to the following implementation. example.

[0052] see figure 1 , the embodiment of the present invention includes the following steps:

[0053] 1. Design cascaded deep convolutional neural networks. For the input image, the image is adjusted to three different scales by means of mean pooling (ave-pooling), which is used as the input of three cascaded sub-networks to construct an image pyramid.

[0054] A1. The first sub-network of the cascade is a small fully convolutional network whose input image size is resized to 56×56 for extracting coarse-grained features of the input image. For the first few layers of a small ful...

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 face attribute recognition method of a deep neural network based on cascaded multi-task learning and relates to the computer vision technology. Firstly, a cascaded deep convolutional neural network is designed, then multi-task learning is used for each cascaded sub-network in the cascaded deep convolutional neural network, four tasks of face classification, border regression, face key point detection and face attribute analysis are learned simultaneously, then a dynamic loss weighting mechanism is used in the deep convolutional neural network based on the cascaded multi-task learning to calculate the loss weights of face attributes, finally a face attribute recognition result of a last cascaded sub-network is used as the final face attribute recognition result based on a trained network model. A cascading method is used to jointly train three different sub-networks, end-to-end training is achieved, the result of face attribute recognition is optimized, different from the use of fixed loss weights in a loss function, a difference between the face attributes present is considered in the invention.

Description

technical field [0001] The invention relates to computer vision technology, in particular to a face attribute recognition method based on cascaded multi-task learning deep neural network. Background technique [0002] In the past few years, face attribute recognition has attracted the attention of more and more experts and scholars in the field of computer vision and pattern recognition. The goal of face attribute recognition is to predict the face attributes contained in a given face image, including smile, gender, attractiveness, etc. Face attribute recognition has a wide range of practical applications, including face verification, image search, and image retrieval. However, due to the changes in face appearance, such as face perspective, illumination, expression, etc., face attribute recognition is still a great challenge. [0003] At present, due to the outstanding performance of convolutional neural networks, many face attribute recognition works use convolutional ne...

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
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/172G06N3/045
Inventor 严严庄妮王菡子
Owner XIAMEN UNIV
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