A Review of the Autoencoder and Its Variants: A Comparative Perspective from Target Recognition in Synthetic-Aperture Radar Images

Dong, Ganggang; Liao, Guisheng; Liu, Hongwei; Kuang, Gangyao

doi:10.1109/mgrs.2018.2853555

Cited by 156 publications

(73 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For network depths and the size of hidden layers, as the network deepened, the classification accuracies became higher. However, the network depth was not as deep as possible [50,53]. When the network contained more than three layers, the performance did not increase any more.…”

Section: Network Construction and Parameter Optimization Of An S-saementioning

confidence: 96%

See 1 more Smart Citation

Feature Dimension Reduction Using Stacked Sparse Auto-Encoders for Crop Classification with Multi-Temporal, Quad-Pol SAR Data

Guo

Ning

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Crop classification in agriculture is one of important applications for polarimetric synthetic aperture radar (PolSAR) data. For agricultural crop discrimination, compared with single-temporal data, multi-temporal data can dramatically increase crop classification accuracies since the same crop shows different external phenomena as it grows up. In practice, the utilization of multi-temporal data encounters a serious problem known as a “dimension disaster”. Aiming to solve this problem and raise the classification accuracy, this study developed a feature dimension reduction method using stacked sparse auto-encoders (S-SAEs) for crop classification. First, various incoherent scattering decomposition algorithms were employed to extract a variety of detailed and quantitative parameters from multi-temporal PolSAR data. Second, based on analyzing the configuration and main parameters for constructing an S-SAE, a three-hidden-layer S-SAE network was built to reduce the dimensionality and extract effective features to manage the “dimension disaster” caused by excessive scattering parameters, especially for multi-temporal, quad-pol SAR images. Third, a convolutional neural network (CNN) was constructed and employed to further enhance the crop classification performance. Finally, the performances of the proposed strategy were assessed with the simulated multi-temporal Sentinel-1 data for two experimental sites established by the European Space Agency (ESA). The experimental results showed that the overall accuracy with the proposed method was raised by at least 17% compared with the long short-term memory (LSTM) method in the case of a 1% training ratio. Meanwhile, for a CNN classifier, the overall accuracy was almost 4% higher than those of the principle component analysis (PCA) and locally linear embedded (LLE) methods. The comparison studies clearly demonstrated the advantage of the proposed multi-temporal crop classification methodology in terms of classification accuracy, even with small training ratios.

show abstract

Section: Network Construction and Parameter Optimization Of An S-saementioning

confidence: 96%

“…where λ is used to control the regularization strength, u is the number of hidden layers, and Ω weights is the weight attenuation term named L2 regularization. By using the Stochastic gradient descent (SGD) algorithm, the weight matrix and bias are trained and optimized [53].…”

Section: Of 26mentioning

confidence: 99%

Feature Dimension Reduction Using Stacked Sparse Auto-Encoders for Crop Classification with Multi-Temporal, Quad-Pol SAR Data

Guo

Ning

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The labelled benchmarks are too small to train a supervised deep network effectively, and overfitting caused by limited labelled samples is often one of the main causes of performance degradation of the supervised model. To handle this problem, various unsupervised DL models are employed and developed, including the autoencoder (AE) [9,10], the generative adversarial network (GAN) [11,12], and the restricted Boltzmann machine (RBM) [13]. Due to the fact of its simple implementation and attractive computational cost, the AE has widely been used in SAR ATR which minimizes the distortion between the inputs and the reconstructions to guarantee that the mapping process preserves the information of the inputs.…”

Section: Introductionmentioning

confidence: 99%

“…Another way to promote the performance of the AE models with a limited training dataset is to incorporate prior knowledge in the model with certain regularization terms and task-specific cost functions. The training process of the AE refers to estimating the trainable parameters of the model and can be achieved by optimizing the objective function consisting of a reconstruction loss and certain regularization terms [9]. In References [30,31], the supervised information was embedded in the cost function by designing label-related regularization terms.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images

Tian

Lin

Gao

et al. 2020

Sensors

View full text Add to dashboard Cite

Although unsupervised representation learning (RL) can tackle the performance deterioration caused by limited labeled data in synthetic aperture radar (SAR) object classification, the neglected discriminative detailed information and the ignored distinctive characteristics of SAR images can lead to performance degradation. In this paper, an unsupervised multi-scale convolution auto-encoder (MSCAE) was proposed which can simultaneously obtain the global features and local characteristics of targets with its U-shaped architecture and pyramid pooling modules (PPMs). The compact depth-wise separable convolution and the deconvolution counterpart were devised to decrease the trainable parameters. The PPM and the multi-scale feature learning scheme were designed to learn multi-scale features. Prior knowledge of SAR speckle was also embedded in the model. The reconstruction loss of the MSCAE was measured by the structural similarity index metric (SSIM) of the reconstructed data and the images filtered by the improved Lee sigma filter. A speckle suppression restriction was also added in the objective function to guarantee that the speckle suppression procedure would take place in the feature learning stage. Experimental results with the MSTAR dataset under the standard operating condition and several extended operating conditions demonstrated the effectiveness of the proposed model in SAR object classification tasks.

show abstract

“…As is typical of neural networks, the architecture of the autoencoder is exposed to multiple training examples with expected output values, and weights are progressively altered through backpropagation [11], [13]. Eventually, the network converges on a set of connection weights that maximize the correspondence between the inputs and the outputs (which, in this case, are similar to the inputs, albeit generated only from the limited number of hidden nodes).…”

Section: Introductionmentioning

confidence: 99%

A Sequential Autoencoder for Teleconnection Analysis

Eastman

2020

Remote Sensing

View full text Add to dashboard Cite

Many aspects of the earth system are known to have preferred patterns of variability, variously known in the atmospheric sciences as modes or teleconnections. Approaches to discovering these patterns have included principal components analysis and empirical orthogonal teleconnection (EOT) analysis. The latter is very effective but is computationally intensive. Here, we present a sequential autoencoder for teleconnection analysis (SATA). Like EOT, it discovers teleconnections sequentially, with subsequent analyses being based on residual series. However, unlike EOT, SATA uses a basic linear autoencoder as the primary tool for analysis. An autoencoder is an unsupervised neural network that learns an efficient neural representation of input data. With SATA, the input is an image time series and the neural representation is a unidimensional time series. SATA then locates the 0.5% of locations with the strongest correlation with the neural representation and averages their temporal vectors to characterize the teleconnection. Evaluation of the procedure showed that it is several orders of magnitude faster than other approaches to EOT, produces teleconnection patterns that are more strongly correlated to well-known teleconnections, and is particularly effective in finding teleconnections with multiple centers of action (such as dipoles).

show abstract

A Review of the Autoencoder and Its Variants: A Comparative Perspective from Target Recognition in Synthetic-Aperture Radar Images

Cited by 156 publications

References 87 publications

Feature Dimension Reduction Using Stacked Sparse Auto-Encoders for Crop Classification with Multi-Temporal, Quad-Pol SAR Data

Feature Dimension Reduction Using Stacked Sparse Auto-Encoders for Crop Classification with Multi-Temporal, Quad-Pol SAR Data

A Multi-Scale U-Shaped Convolution Auto-Encoder Based on Pyramid Pooling Module for Object Recognition in Synthetic Aperture Radar Images

A Sequential Autoencoder for Teleconnection Analysis

Contact Info

Product

Resources

About