Object attribute prediction method, device and equipment

Abstract

The invention relates to a computer vision technology, in particular to an object attribute prediction method, device and equipment, and an object attribute prediction model construction method, device and equipment, and aims to solve the problems of relatively low prediction accuracy and relatively high calculation resource consumption in the prior art. All attributes are put together for featureextraction by using a shared feature extraction network; after the feature extraction network, according to the division standards of the ordered attributes and the disordered attributes, different types of attributes are placed in attribute prediction networks of a classification structure and a regression structure for processing, and different loss functions are adopted by the attribute prediction networks of different structures. According to the scheme provided by the invention, the correlation between the attributes is fully utilized, efficient multi-attribute feature sharing is realized, more effective features are mined out, and the heterogeneity between the attributes is fully utilized to realize attribute prediction for separately managing the ordered attributes and the disordered attributes, so that the prediction accuracy can be improved, and the computing resources are saved.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer vision, and in particular, to a method, device and device for predicting object attributes, and a method, device and device for constructing an object attribute prediction model. Background technique [0002] Human attribute detection technology refers to determining the attributes of a person, such as gender, age, race, height, etc., by using the detailed features displayed on the image for any given image of a person. After detecting the attributes of people, functions such as screening, classification, retrieval and even identification of portraits can be realized. [0003] At present, the human attribute detection technology is usually implemented by the human attribute prediction method based on the deep learning framework. In the human attribute prediction method based on the deep learning framework, a typical technical solution is: first, convert the ordered attributes (such a...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide an object attribute prediction method and an object attribute prediction model building method, as well as corresponding devices and equipment, so as to solve the problems of low prediction accuracy and high consumption of computing resources in the prior art

Images