Interpretability of Deep Network Structures for SAR Image Target Recognition Based on Generative Adversarial Mask

Yuhang Zhang, Jie Geng, Wen Jiang

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

1 Scopus citations

Abstract

Deep neural networks (DNN) have been widely used in SAR image Target recognition and have achieved great success. However, the black box attribute of DNN makes the mechanism of the network inexplicable and confusing. In this paper, a network layer analysis model based on generative adversarial mask (GAM) is proposed to enhance the structure interpretability of DNNs. Inspired by network adaptive search, we introduce a mask layer and construct a layer analysis model. After sparse training and generative adversarial training, the contribution of the network layer can be calculated based on the mask layer parameters. We conducted sufficient experiments on several typical DNNs to verify the effectiveness of GAM.

Original languageEnglish
Title of host publicationProceedings of 2023 IEEE International Conference on Unmanned Systems, ICUS 2023
EditorsRong Song
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages786-791
Number of pages6
ISBN (Electronic)9798350316308
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Unmanned Systems, ICUS 2023 - Hefei, China
Duration: 13 Oct 202315 Oct 2023

Publication series

NameProceedings of 2023 IEEE International Conference on Unmanned Systems, ICUS 2023

Conference

Conference2023 IEEE International Conference on Unmanned Systems, ICUS 2023
Country/TerritoryChina
CityHefei
Period13/10/2315/10/23

Keywords

  • Deep neural network
  • SAR image recognition
  • Structure interpretability

Fingerprint

Dive into the research topics of 'Interpretability of Deep Network Structures for SAR Image Target Recognition Based on Generative Adversarial Mask'. Together they form a unique fingerprint.

Cite this