TAI-SARNET: Deep Transferred Atrous-Inception CNN for Small Samples SAR ATR

Ying, Zilu; Chen, Xuan; Zhai, Yongjie; Sun, Bing; Li, Jingwen; Deng, Wenbo; Mai, Chaoyun; Wang, Faguan; Labati, Ruggero Donida; Piuri, Vincenzo; Scotti, Fabio

doi:10.3390/s20061724

Cited by 32 publications

(12 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 5 summarizes the recognition results with small sample sizes. The results of MobileNet were obtained from our implementation, while the results of TAI-SARNET and TAI-SARNET-TF were from [ 39 ]. Our model performs better than the competitors in small-data scenarios.…”

Section: Resultsmentioning

confidence: 99%

SAR Target Recognition via Meta-Learning and Amortized Variational Inference

Wang

Zhang

2020

Sensors

View full text Add to dashboard Cite

The challenge of small data has emerged in synthetic aperture radar automatic target recognition (SAR-ATR) problems. Most SAR-ATR methods are data-driven and require a lot of training data that are expensive to collect. To address this challenge, we propose a recognition model that incorporates meta-learning and amortized variational inference (AVI). Specifically, the model consists of global parameters and task-specific parameters. The global parameters, trained by meta-learning, construct a common feature extractor shared between all recognition tasks. The task-specific parameters, modeled by probability distributions, can adapt to new tasks with a small amount of training data. To reduce the computation and storage cost, the task-specific parameters are inferred by AVI implemented with set-to-set functions. Extensive experiments were conducted on a real SAR dataset to evaluate the effectiveness of the model. The results of the proposed approach compared with those of the latest SAR-ATR methods show the superior performance of our model, especially on recognition tasks with limited data.

show abstract

Section: Resultsmentioning

confidence: 99%

SAR Target Recognition via Meta-Learning and Amortized Variational Inference

Wang

Zhang

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Similar to paper [24], the method completed the re-calibration of weights from channel domain and spatial domain respectively. Finally, the recognition rate of this model on MSTAR data set reached 99.35%, Compared with A-Convnet [25] and TAI-Sarnet [27], this model not only effectively reduced the number of parameters, but also achieved a higher recognition rate. Even so, the complexity of the model is still relatively large, reaching 5.12M, and there is still much room for improvement.…”

Section: B Convolutional Neural Network With Attentionmentioning

confidence: 88%

Synthetic Aperture Radar SAR Image Target Recognition Algorithm Based on Attention Mechanism

et al. 2021

View full text Add to dashboard Cite

SAR images contain a large amount of noise, and related algorithms will cause high complexity when increasing the accuracy. To overcome this problem, a neural network model based on the attention mechanism was proposed in this paper. The model extracted information in two stages. It gradually extracts high-level features by reducing noise first and then adding hybrid attention. First, use dual-channel one-dimensional convolution to reconstruct the residual shrinkage network to construct a lightweight and efficient feature module, which improved the information extraction of the module with the consumption of a small amount of computing resources. Then, it was used as the backbone for model construction. Subsequently, mixed adaptive pooling was adopted to improve the maximum pooling. After that, dimensionality was reduced by pooling and linear interpolation was used to increase dimensionality, so as to generate feature weights of mixed dimension. Tests were performed on MSTAR dataset. The results showed that compared with the advanced algorithms, the proposed model in this paper can greatly reduce the amount of parameters and complexity while ensuring accuracy. The robustness test demonstrated that the model can effectively identify images with noise being added.

show abstract

“…In recent years, deep learning-based methods such as the convolutional neural network (CNN) have rapidly replaced conventional pattern recognition methods as they dramatically improved the performances by automatically learning the discriminative features for SAR target recognition. In most relevant studies, excellent SAR target recognition performances were achieved by the combination of the CNN and pattern recognition [ 10 , 11 , 12 , 13 ], extraction of multi-view features [ 14 , 15 , 16 ], adoption of state-of-the-art deep learning network structures [ 17 , 18 , 19 , 20 , 21 , 22 ], fusion of feature maps [ 23 ], data augmentation [ 24 , 25 ], and transfer learning [ 26 , 27 ].…”

Section: Introductionmentioning

confidence: 99%

SAR ATR for Limited Training Data Using DS-AE Network

Park

Seo

Yoo

2021

Sensors

View full text Add to dashboard Cite

Although automatic target recognition (ATR) with synthetic aperture radar (SAR) images has been one of the most important research topics, there is an inherent problem of performance degradation when the number of labeled SAR target images for training a classifier is limited. To address this problem, this article proposes a double squeeze-adaptive excitation (DS-AE) network where new channel attention modules are inserted into the convolutional neural network (CNN) with a modified ResNet18 architecture. Based on the squeeze-excitation (SE) network that employs a representative channel attention mechanism, the squeeze operation of the DS-AE network is carried out by additional fully connected layers to prevent drastic loss in the original channel information. Then, the subsequent excitation operation is performed by a new activation function, called the parametric sigmoid, to improve the adaptivity of selective emphasis of the useful channel information. Using the public SAR target dataset, the recognition rates from different network structures are compared by reducing the number of training images. The analysis results and performance comparison demonstrate that the DS-AE network showed much more improved SAR target recognition performances for small training datasets in relation to the CNN without channel attention modules and with the conventional SE channel attention modules.

show abstract

TAI-SARNET: Deep Transferred Atrous-Inception CNN for Small Samples SAR ATR

Cited by 32 publications

References 50 publications

SAR Target Recognition via Meta-Learning and Amortized Variational Inference

SAR Target Recognition via Meta-Learning and Amortized Variational Inference

Synthetic Aperture Radar SAR Image Target Recognition Algorithm Based on Attention Mechanism

SAR ATR for Limited Training Data Using DS-AE Network

Contact Info

Product

Resources

About