Skip to main navigation Skip to search Skip to main content

Generalization and Robustness Evaluation Method for Target Classification Based on Convolutional Neural Network

  • Jiashu Yang
  • , Dan Guo
  • , Jia Zhai
  • , Xiaoyong Du
  • , Chengzu Bai
  • , Pengyu Wang
  • , Huanyu Liu*
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • Beijing Institute of Environmental Characteristics
  • Beijing Institute of Applied Meteorology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The reliability of the existing target classification system lacks a perfect evaluation method. In order to improve the reliability of the target classification system and the adaptability of intelligent air combat scenarios, a data-driven reliability evaluation method is proposed, which is based on the three elements of the target classification system “data + algorithm + platform.” The credibility evaluation model based on black box and white box is proposed. The generalization ability evaluation model of the target classification system and the robust ability evaluation model of the target classification system are constructed to evaluate the working ability of the system in many aspects, which fundamentally guarantees the reliability of the target classification system. The reliability evaluation method of the target classification system is established, which can be used to support and improve the reliability evaluation technology system of the target classification system, improve the reliability analysis ability of the target classification system, and provide suggestions on the usability of the classification algorithm.

Original languageEnglish
Title of host publicationAdvances in Intelligent Information Hiding and Multimedia Signal Processing, Volume 1 - Proceeding of the 19th International Conference on IIH-MSP in conjunction with 11th International Conference on Orange Technology, Applications and Tools
EditorsShih-Pang Tseng, Anand Paul, Jeng-Shyang Pan, Margarita Favorskaya
PublisherSpringer Science and Business Media Deutschland GmbH
Pages187-197
Number of pages11
ISBN (Print)9789819787630
DOIs
StatePublished - 2025
Event19th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2023, in conjunction with the 11th International Conference on Orange Technology, Applications, and Tools, ICOT 2023 - Daegu, Korea, Republic of
Duration: 5 Dec 20237 Dec 2023

Publication series

NameSmart Innovation, Systems and Technologies
Volume415
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference19th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2023, in conjunction with the 11th International Conference on Orange Technology, Applications, and Tools, ICOT 2023
Country/TerritoryKorea, Republic of
CityDaegu
Period5/12/237/12/23

Keywords

  • Generalization ability
  • Reliability assessment
  • Robustness ability
  • Target classification system

Fingerprint

Dive into the research topics of 'Generalization and Robustness Evaluation Method for Target Classification Based on Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this