Incremental learning using feature labels for synthetic aperture radar automatic target recognition
Abstract Although deep neural network technology brings high recognition accuracy to the field of synthetic aperture radar image‐based automatic target recognition, it also produces the catastrophic forgetting problem. Here, a new incremental learning method that can extract more information about o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-11-01
|
| Series: | IET Radar, Sonar & Navigation |
| Online Access: | https://doi.org/10.1049/rsn2.12303 |
| _version_ | 1797996623935045632 |
|---|---|
| author | Chao Hu Ming Hao Wenying Wang Yong Yang Daoqing Wu |
| author_facet | Chao Hu Ming Hao Wenying Wang Yong Yang Daoqing Wu |
| author_sort | Chao Hu |
| collection | DOAJ |
| description | Abstract Although deep neural network technology brings high recognition accuracy to the field of synthetic aperture radar image‐based automatic target recognition, it also produces the catastrophic forgetting problem. Here, a new incremental learning method that can extract more information about old data is proposed. Based on the rehearsal method, the authors’ method adds extra linear layers after the feature extractor of the network before training on new incremental data and uses the network to generate distilled labels for incremental training. Through experiments on the moving and stationary target acquisition and recognition data set, we conclude that, when the old model has good performance, our method has better performance than other typical incremental learning methods on small data sets. |
| first_indexed | 2024-04-11T10:20:20Z |
| format | Article |
| id | doaj.art-407a916d36e34fb8b9d77993a0b22f12 |
| institution | Directory Open Access Journal |
| issn | 1751-8784 1751-8792 |
| language | English |
| last_indexed | 2024-04-11T10:20:20Z |
| publishDate | 2022-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Radar, Sonar & Navigation |
| spelling | doaj.art-407a916d36e34fb8b9d77993a0b22f122022-12-22T04:29:46ZengWileyIET Radar, Sonar & Navigation1751-87841751-87922022-11-0116111872188010.1049/rsn2.12303Incremental learning using feature labels for synthetic aperture radar automatic target recognitionChao Hu0Ming Hao1Wenying Wang2Yong Yang3Daoqing Wu4Nanjing Institute of Electronic Technology Nanjing ChinaNanjing Institute of Electronic Technology Nanjing ChinaNanjing Institute of Electronic Technology Nanjing ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System National University of Defense Technology Changsha ChinaNanjing Institute of Electronic Technology Nanjing ChinaAbstract Although deep neural network technology brings high recognition accuracy to the field of synthetic aperture radar image‐based automatic target recognition, it also produces the catastrophic forgetting problem. Here, a new incremental learning method that can extract more information about old data is proposed. Based on the rehearsal method, the authors’ method adds extra linear layers after the feature extractor of the network before training on new incremental data and uses the network to generate distilled labels for incremental training. Through experiments on the moving and stationary target acquisition and recognition data set, we conclude that, when the old model has good performance, our method has better performance than other typical incremental learning methods on small data sets.https://doi.org/10.1049/rsn2.12303 |
| spellingShingle | Chao Hu Ming Hao Wenying Wang Yong Yang Daoqing Wu Incremental learning using feature labels for synthetic aperture radar automatic target recognition IET Radar, Sonar & Navigation |
| title | Incremental learning using feature labels for synthetic aperture radar automatic target recognition |
| title_full | Incremental learning using feature labels for synthetic aperture radar automatic target recognition |
| title_fullStr | Incremental learning using feature labels for synthetic aperture radar automatic target recognition |
| title_full_unstemmed | Incremental learning using feature labels for synthetic aperture radar automatic target recognition |
| title_short | Incremental learning using feature labels for synthetic aperture radar automatic target recognition |
| title_sort | incremental learning using feature labels for synthetic aperture radar automatic target recognition |
| url | https://doi.org/10.1049/rsn2.12303 |
| work_keys_str_mv | AT chaohu incrementallearningusingfeaturelabelsforsyntheticapertureradarautomatictargetrecognition AT minghao incrementallearningusingfeaturelabelsforsyntheticapertureradarautomatictargetrecognition AT wenyingwang incrementallearningusingfeaturelabelsforsyntheticapertureradarautomatictargetrecognition AT yongyang incrementallearningusingfeaturelabelsforsyntheticapertureradarautomatictargetrecognition AT daoqingwu incrementallearningusingfeaturelabelsforsyntheticapertureradarautomatictargetrecognition |