TY - GEN
T1 - Generalization and Robustness Evaluation Method for Target Classification Based on Convolutional Neural Network
AU - Yang, Jiashu
AU - Guo, Dan
AU - Zhai, Jia
AU - Du, Xiaoyong
AU - Bai, Chengzu
AU - Wang, Pengyu
AU - Liu, Huanyu
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - 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.
AB - 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.
KW - Generalization ability
KW - Reliability assessment
KW - Robustness ability
KW - Target classification system
UR - https://www.scopus.com/pages/publications/105003903833
U2 - 10.1007/978-981-97-8764-7_18
DO - 10.1007/978-981-97-8764-7_18
M3 - 会议稿件
AN - SCOPUS:105003903833
SN - 9789819787630
T3 - Smart Innovation, Systems and Technologies
SP - 187
EP - 197
BT - Advances 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
A2 - Tseng, Shih-Pang
A2 - Paul, Anand
A2 - Pan, Jeng-Shyang
A2 - Favorskaya, Margarita
PB - Springer Science and Business Media Deutschland GmbH
T2 - 19th 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
Y2 - 5 December 2023 through 7 December 2023
ER -