Target Classification Using the Deep Convolutional Networks for SAR Images

Chen, Sizhe; Wang, Haipeng; Xu, Feng; Jin, Ya‐Qiu

doi:10.1109/tgrs.2016.2551720

Cited by 1,077 publications

(611 citation statements)

References 22 publications

Supporting

Mentioning

603

Contrasting

Unclassified

Order By: Relevance

“…It is 8.67%, 5.43%, 5.68%, 2.85%, 4.09% better than SVM, sparse representation of monogenic signal (MSRC) [18], tri-task joint sparse representation (TJSR) [48], supervised discriminative dictionary learning and sparse representation (SDDLSR) [8] and joint dynamic sparse representation (JDSR) [49]. In addition, our method can achieve a comparable performance to the state-of-the-art methods based on deep learning (A-ConvNet [24] and DCHUN [50]), shown in Figure 12. In order to verify the advantage of our method for a further step, experiments have been conducted on different sizes of training dataset.…”

Section: The Effectiveness Of Transfer Learningmentioning

confidence: 92%

“…Moreover, Wilmanski et al [32] explored different learning algorithms of training CNNs, finding that the AdaDelta technique that can update the various learning rates of hyper-parameters outperformed the other techniques such as stochastic gradient descent (SGD) and AdaGrad. Recently, in [24], a five-layer all-convolutional network was proposed. The authors adopted a drop-out method in a convolution layer and removed the fully connected layer to avoid over-fitting since the limited training data was insufficient to train the deep CNNs.…”

Section: Sar Target Recognition With Cnnsmentioning

confidence: 99%

“…In order to verify the advantage of our method for a further step, experiments have been conducted on different sizes of training dataset. By randomly selecting 200, 100, 50 samples in each category of MSTAR training set as the training samples, respectively, we experiment with the A-ConvNet method [24], the baseline (written as CNN-baseline), and the proposed method without bypass (written as CNN-TL) and proposed method with bypass (written as CNN-TL-bypass). The recognition rate of each method is shown in Figure 13.…”

Section: The Effectiveness Of Transfer Learningmentioning

confidence: 99%

“…Unfortunately, there exists no large-scale annotated SAR target dataset comparable to ImageNet, as data acquisition is expensive and quality annotation is costly. Limited by inadequate data in SAR target recognition, the current studies related to deep CNNs mainly focus on augmenting the training data [23], designing a less complex network for a specific problem and making efforts on avoiding overfitting [24]. Generally, the deeper and wider networks can develop more abstraction and more features.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data

2017

View full text Add to dashboard Cite

Abstract:Tremendous progress has been made in object recognition with deep convolutional neural networks (CNNs), thanks to the availability of large-scale annotated dataset. With the ability of learning highly hierarchical image feature extractors, deep CNNs are also expected to solve the Synthetic Aperture Radar (SAR) target classification problems. However, the limited labeled SAR target data becomes a handicap to train a deep CNN. To solve this problem, we propose a transfer learning based method, making knowledge learned from sufficient unlabeled SAR scene images transferrable to labeled SAR target data. We design an assembled CNN architecture consisting of a classification pathway and a reconstruction pathway, together with a feedback bypass additionally. Instead of training a deep network with limited dataset from scratch, a large number of unlabeled SAR scene images are used to train the reconstruction pathway with stacked convolutional auto-encoders (SCAE) at first. Then, these pre-trained convolutional layers are reused to transfer knowledge to SAR target classification tasks, with feedback bypass introducing the reconstruction loss simultaneously. The experimental results demonstrate that transfer learning leads to a better performance in the case of scarce labeled training data and the additional feedback bypass with reconstruction loss helps to boost the capability of classification pathway.

show abstract

Section: The Effectiveness Of Transfer Learningmentioning

confidence: 92%

Section: Sar Target Recognition With Cnnsmentioning

confidence: 99%

Section: The Effectiveness Of Transfer Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data

2017

View full text Add to dashboard Cite

show abstract

“…Tang et al [11] used a deep neural network for ship detection. Convolution neural networks have been widely used in remote sensing for scene classification [12], image segmentation [13] and target classification in SAR data [14], and recurrent neural network is utilized for learning land cover change [15]. Stacked Denoising Autoencoder (SDAE), an improved model of SAE, has made outstanding achievements in areas such as speech recognition [16] and other domains.…”

Section: Stacked Denoising Autoencoder Modelmentioning

confidence: 99%

Remote Sensing Image Classification Based on Stacked Denoising Autoencoder

2017

View full text Add to dashboard Cite

Focused on the issue that conventional remote sensing image classification methods have run into the bottlenecks in accuracy, a new remote sensing image classification method inspired by deep learning is proposed, which is based on Stacked Denoising Autoencoder. First, the deep network model is built through the stacked layers of Denoising Autoencoder. Then, with noised input, the unsupervised Greedy layer-wise training algorithm is used to train each layer in turn for more robust expressing, characteristics are obtained in supervised learning by Back Propagation (BP) neural network, and the whole network is optimized by error back propagation. Finally, Gaofen-1 satellite (GF-1) remote sensing data are used for evaluation, and the total accuracy and kappa accuracy reach 95.7% and 0.955, respectively, which are higher than that of the Support Vector Machine and Back Propagation neural network. The experiment results show that the proposed method can effectively improve the accuracy of remote sensing image classification.

show abstract

Bibliography

2021

Deep Learning for the Earth Sciences

View full text Add to dashboard Cite

Target Classification Using the Deep Convolutional Networks for SAR Images

Cited by 1,077 publications

References 22 publications

Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data

Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data

Remote Sensing Image Classification Based on Stacked Denoising Autoencoder

Bibliography

Contact Info

Product

Resources

About