Domain Knowledge Powered Two-Stream Deep Network for Few-Shot SAR Vehicle Recognition

Zhang, Linbin; Leng, Xiangguang; Feng, Sijia; Ma, Xiaojie; Ji, Kefeng; Kuang, Gangyao; Liu, Li

doi:10.1109/tgrs.2021.3116349

Cited by 59 publications

(28 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with real images, simulated SAR images' categories and depression angles are more abundant. The experimental setting used in this section is referenced from DKTS-N [23]. This method achieves state-of-the-art performance in cross-domain few-shot SAR-ATR.…”

Section: Cross-domain Few-shot Recognitionmentioning

confidence: 99%

“…The characteristics of SAR targets can be used as domain-related knowledge to assist the training of the SAR-ATR model, thus improving the model's accuracy in FSC scenarios. Zhang et al [23] designed a dual-stream CNN powered by domain knowledge such as azimuth angles and phase information of SAR images. To exploit electromagnetic scattering characteristics of SAR targets, Wang et al [24] performed sub-band decomposition on complex-valued SAR images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Few-Shot SAR Target Recognition Based on Deep Kernel Learning

et al. 2022

View full text Add to dashboard Cite

Deep learning methods have achieved state-of-the-art performance on synthetic aperture radar (SAR) target recognition tasks in recent years. However, obtaining sufficient SAR images for training these deep learning methods is costly in time and labor. This paper focuses on recognizing targets with a few training samples, that is, few-shot target recognition. We combine deep neural networks' powerful feature representation capabilities with the nonparametric flexibility of Gaussian processes (GPs) and propose a fewshot recognition model based on deep kernel learning. Deep neural networks map input samples into a lowdimensional embedding space. GPs employ a family of kernel functions to measure the similarity between embedded samples and classify them. During training, the model builds diverse related tasks to learn kernel functions with parameters shared across few-shot tasks. These learned kernel functions define common prior knowledge that can be transferred to unseen tasks. During testing, the model can recognize novel tasks with a few samples based on learned kernel functions. We conducted extensive experiments on a widely-used real SAR dataset to evaluate the model's effectiveness. The test results demonstrate that our model is superior to several recently proposed few-shot recognition methods.INDEX TERMS Synthetic aperture radar (SAR), target recognition, deep kernel learning, few-shot classification

show abstract

Section: Cross-domain Few-shot Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Few-Shot SAR Target Recognition Based on Deep Kernel Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In [10], [11], the authors first performed the pre-training technique on unlabeled SAR images or optical images to acquire prior knowledge, and then transferred learned knowledge to the real SAR-ATR task. Moreover, the domain knowledge of SAR imaging (such as range/azimuth angle information [12], [16], attributed scattering centers (ASCs) features [17]- [21], multi-scale rotation invariant haar-like features of SAR images [30]) and the extracted features by DL model are fused to effectively and efficiently alleviate the overfitting at the limited data scenarios.…”

Section: Introductionmentioning

confidence: 99%

LW-CMDANet: A Novel Attention Network for SAR Automatic Target Recognition

Lang

Feng

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Deep learning based synthetic aperture radar automatic target recognition (SAR-ATR) plays an significant role in the military and civilian fields. However, data limitation and large computational cost are still severe challenges in actual application of SAR-ATR. To improve the performance of CNN model with limited data samples in SAR-ATR, this paper proposes a novel multi-domain feature subspaces fusion representation learning method, i.e., a lightweight cascaded multi-domain attention network, namely LW-CMDANet. First, we design a four-layer CNN model to perform hierarchical features representation learning via hinge loss function, which can efficiently alleviate the overfitting problem of CNN model by a non-greedy training style with small dataset. Then, a cascaded multi-domain attention module, based on discrete cosine transform and discrete wavelet transform, is embedded into the previous CNN to further complete the classspecific features extraction from both frequency and wavelet transform domains of the input feature maps. Thus, the multidomain attention can enhance the features extraction ability of previous non-greedy learning manner, to effectively improve the recognition accuracy of CNN model. Experimental results on small SAR datasets show that our proposed method can achieve better or competitive performance than many current existing state-of-the-art methods in terms of recognition accuracy and computational cost.

show abstract

“…In order to increase the feature difference between categories, Zhang et al [23] designed a two-stream deep network and introduced SAR domain knowledge such as target azimuth and phase into the CNN to assist in classification. For SAR classification tasks, existing methods mainly introduce prior knowledge and fuse features at the network input, ignoring the category labels that actually guide the classification at the network output.…”

Section: Introductionmentioning

confidence: 99%

SAR Target Classification Based on Multiscale Attention Super-Class Network

Wang

Song

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The convolutional neural network (CNN) is widely used in synthetic aperture radar (SAR) target recognition, but conventional CNN mainly adopts a single-scale convolutional kernel, resulting in losing part of the feature information of targets and does not pay enough attention to significant features. On the other hand, conventional CNN approaches only assign fine-class labels to SAR targets, ignoring the high-level semantics information of similar categories, which reduces the feature differences between categories and the generalization ability of the model. Therefore, this paper proposes a multi-scale attention super-class CNN (MSA-SCNN) for SAR target classification. Firstly, MSA-SCNN combines multi-scale feature fusion with the attention module to improve the integrity of SAR target feature representation. The attention module includes channel and spatial attention modules, which realize the weighted enhancement of different scale features. Additionally, MSA-SCNN introduces super-class labels to increase the feature difference between categories. The classification stage consists of a fine-class branch and a super-class branch, and the features trained on the superclass branch are fused to the fine-class branch to improve the network's fine classification ability. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset and the FUSAR-Ship dataset show that the proposed MSA-SCNN outperforms many current existing state-of-the-art methods.

show abstract

Domain Knowledge Powered Two-Stream Deep Network for Few-Shot SAR Vehicle Recognition

Cited by 59 publications

References 62 publications

Few-Shot SAR Target Recognition Based on Deep Kernel Learning

Few-Shot SAR Target Recognition Based on Deep Kernel Learning

LW-CMDANet: A Novel Attention Network for SAR Automatic Target Recognition

SAR Target Classification Based on Multiscale Attention Super-Class Network

Contact Info

Product

Resources

About