Class regularization method and system for domain adaptive target detection

A target detection and domain adaptive technology, applied in the field of target detection based on deep learning, can solve problems such as whether the alignment has not been really considered, the domain adaptive target detection model is suboptimal, and the alignment of features of the same category is not sufficient. Achieve the effects of realizing a virtuous circle, ensuring discriminability, and enhancing classification accuracy

Active Publication Date: 2022-04-22
湖南大学无锡智能控制研究院
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, whether the features of the source domain and the target domain are aligned at the category level after adaptation has not been really considered.
In cross-domain scenarios, misalignment of features of different categories, or insufficient alignment of features of the same category, may lead to negative transfer of features from two domains, and the trained domain-adaptive object detection model can only achieve suboptimal performance.

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
  • Class regularization method and system for domain adaptive target detection
  • Class regularization method and system for domain adaptive target detection
  • Class regularization method and system for domain adaptive target detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0072] The following terms are involved in this embodiment, and their meanings are explained as follows for ease of understanding. Those skilled in the art should understand that the following terms may also have other names, but any other names should be considered consistent with the terms listed herein without departing from their meanings.

[0073] Such as figure 1 and figure 2 As shown, the category regularization method for domain adaptive target detection provided by the embodiment of the present invention includes:

[0074] Step 1, get the feature vector of the region of interest in the source domain and the feature vector of the region of interest in the target domain and its associated Corresponding prediction category and with the said Corresponding prediction category where i and j denote the indices corresponding to the reg...

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 category regularization method and system for domain adaptive target detection, and the method comprises the steps: 1, obtaining a source domain region-of-interest feature vector, a target domain region-of-interest feature vector, a corresponding prediction category and a corresponding prediction category; 2, calculating an inter-category regularization loss function value; and step 4, calculating an intra-class regularization loss function value, and combining the intra-class regularization loss function value as a regularization item into a loss function of the domain self-adaptive target detection framework so as to jointly optimize the domain self-adaptive target detection loss function and the class regularization loss function. According to the method, reasonable and sufficient alignment of the same category of features of the two domains is realized, the risk of negative migration of the features of the two domains is greatly reduced, and the method can be flexibly expanded to various existing domain adaptive target detection frameworks.

Description

technical field [0001] The invention relates to the technical field of object detection based on deep learning, in particular to a category regularization method and system for domain adaptive object detection. Background technique [0002] Current object detection methods based on deep learning usually assume that the data of the training set (called the source domain) and the test set (called the target domain) obey the same probability distribution, but this assumption is often difficult to hold in many practical application scenarios. The domain drift problem caused by differences in data distribution degrades the detection performance of deep object detection models on object domains. Although the degradation of model performance can be mitigated by collecting and labeling more training data, this process is extremely time-consuming and costly. Unsupervised domain adaptation transfers knowledge from a source domain with labeled data to a target domain without labeled d...

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): G06K9/62G06N3/04G06N3/08G06V10/25G06V10/764G06V10/82
CPCG06N3/08G06N3/045G06F18/241
Inventor 王晓伟王惠蒋沛文谢国涛秦兆博秦晓辉边有钢胡满江秦洪懋徐彪丁荣军
Owner 湖南大学无锡智能控制研究院
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