Skip to main navigation Skip to search Skip to main content

Computational interpretability of multilayer preceptron used for SAR image target recognition

  • Beihang University
  • CAS - Institute of Electronics

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

Abstract

The achievement of deep neural networks (DNNs) in the computer vision has aroused great concerns in the synthetic aperture radar (SAR) automatic target recognition (ATR) field. As a simple but effective model, the multilayer perceptron (MLP) is widely used in SAR image target recognition. However, the black-box problem could limit the development of DNNs in SAR ATR. In this paper, we explore the interpretability of MLP from the perspective of computation process of its forward propagation. By using the matrix representation, the function is studied that the angles between parameters and features as well as features magnitudes. Besides, the feature statistics is adopted to discuss the effect of nonlinear activation functions. Finally, some experiments on the MSTAR datasets are carried out and analyzed to demonstrate the effectiveness of the proposed method.

Original languageEnglish
Title of host publication2021 CIE International Conference on Radar, Radar 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1371-1374
Number of pages4
ISBN (Electronic)9781665498142
DOIs
StatePublished - 2021
Event2021 CIE International Conference on Radar, Radar 2021 - Haikou, Hainan, China
Duration: 15 Dec 202119 Dec 2021

Publication series

NameProceedings of the IEEE Radar Conference
Volume2021-December
ISSN (Print)1097-5764
ISSN (Electronic)2375-5318

Conference

Conference2021 CIE International Conference on Radar, Radar 2021
Country/TerritoryChina
CityHaikou, Hainan
Period15/12/2119/12/21

Keywords

  • SAR image target recognition
  • convolutional neural networks
  • interpretability
  • multilayer perceptron

Fingerprint

Dive into the research topics of 'Computational interpretability of multilayer preceptron used for SAR image target recognition'. Together they form a unique fingerprint.

Cite this