2019
DOI: 10.1080/01431161.2019.1641246
|View full text |Cite
|
Sign up to set email alerts
|

Exploiting multi-level deep features via joint sparse representation with application to SAR target recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(4 citation statements)
references
References 38 publications
0
4
0
Order By: Relevance
“… ESENet [ 33 ]: the ESENet is employed for SAR ATR. JSRDeep [ 36 ]: the CNN is developed for feature learning to generate multilayer feature maps. Afterwards, the joint sparse representation is employed to classify the deep feature vectors.…”
Section: Methodsmentioning
confidence: 99%
“… ESENet [ 33 ]: the ESENet is employed for SAR ATR. JSRDeep [ 36 ]: the CNN is developed for feature learning to generate multilayer feature maps. Afterwards, the joint sparse representation is employed to classify the deep feature vectors.…”
Section: Methodsmentioning
confidence: 99%
“…MVL and MTL have rapidly grown in ML and data mining in the past few years, which can obviously improve performance of model learning. In RSP domain, these related methods are popular in DL-based SAR-ATR, e.g., [325], [328], [331], [336], [337], [340], [343], [347]. Therefore, it is necessary to make a brief introduction about the review papers in MVL [36] and MTL [37].…”
Section: B Related Workmentioning
confidence: 99%
“…After finding an effective subset of training samples and constructing a new dictionary by multi-feature joint sparse representation learning as the first stage, the authors utilized multi-task collaborative representation to perform target images classification based on the new dictionary in second stage. A multi-level deep features-based multi-task learning algorithm was developed in [347] for SAR-ATR. This architecture employed joint sparse representation as the basic classifier and achieved an recognition rate of 99.38% on MSTAR under standard operating conditions (SOCs).…”
Section: A Sar Images Processingmentioning
confidence: 99%
“…Based on the compressive sensing theory, SRC was first validated in face recognition [43] and further used in SAR ATR in many related works [40][41][42]. With the progress in deep learning, many novel networks were developed for SAR target recognition [44][45][46][47][48][49][50][51][52][53][54][55][56][57][58][59], in which the convolutional neural network (CNN) is the mostly used. Network architectures including the all-convolutional neural networks (A-ConvNets) [46], enhanced squeeze and excitation network (ESENet) [47], gradually distilled CNN [48], cascade coupled CNN [49], and multistream CNN [50], were developed and applied.…”
Section: Introductionmentioning
confidence: 99%