Target detection model robustness test method based on uncertainty

By using an uncertainty-based robustness testing method for target detection models, we can automatically generate diverse test cases and introduce diverse mutation strategies. This solves the problems of limited test cases and low efficiency in existing technologies, and enables efficient discovery of model vulnerabilities and improved robustness.

CN121902151APending Publication Date: 2026-04-21BEIJING INST OF COMP TECH & APPL
0 Cites 0 Cited by

Patent Information

Application Number
CN202511700410.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-19
Publication Date
2026-04-21

AI Technical Summary

Technical Problem

Existing robustness testing methods for object detection models suffer from limitations in the availability of manually labeled test cases and the need for improved testing efficiency.

Method used

This paper proposes a robustness testing method for target detection models based on uncertainty. Through seed mutation, model prediction, uncertainty analysis and test case expansion, a large number of test cases are automatically generated. Diverse data mutation strategies such as affine transformation and target-level transformation are introduced, and mutation samples are screened in combination with uncertainty index to improve testing efficiency and effectiveness.

Benefits of technology

It enables efficient discovery of model vulnerabilities, improves the robustness of target detection systems, can automatically generate diverse test cases, improves testing efficiency and accuracy, and can more efficiently reveal and fix model errors.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a target detection model robustness test method based on uncertainty, and belongs to the technical field of image processing. The method comprises the steps of seed variation, model prediction, uncertainty analysis, test case amplification and robustness test. Diversified data variation strategies such as affine transformation and target-level transformation of the image are introduced, and target information in the image is changed, so that diversity and aggressiveness of variation samples are enhanced. In addition, the probability of correct prediction of the target is measured through an uncertainty index measurement model. The test cases generated under the guidance of uncertainty have higher value for revealing model vulnerabilities or repairing model errors, potential defects in the aspect of robustness of the target detection model can be more efficiently mined, a large number of test cases can be automatically generated, and the model vulnerabilities can be efficiently found; and the robustness of the target detection system can be improved.
Need to check novelty before this filing date? Find Prior Art