SAR Target Recognition via Meta-Learning and Amortized Variational Inference

Wang, Ke; Zhang, Gong

doi:10.3390/s20205966

Cited by 8 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed in Section 5.1, the VAE amortizes the inference to scale its training to large data sets, making it a popular choice for several applications such as density estimation, lossless compression, and representation learning (Zhang et al, 2022). However, the use of amortized inference during its training phase can lead to poor generalization performance.…”

Section: Generalization Gapmentioning

confidence: 99%

“…However, the use of amortized inference during its training phase can lead to poor generalization performance. In order to tackle this issue, Zhang et al (2022) introduced a training methodology for the recognition network in a VAE to reduce over-fitting to the training data and hence, improve generalization. Due to the lack of sufficient training data, a flexible posterior approximation can lead the recognition network to reduce the overall inference gap but also over-fit to the training data.…”

Section: Generalization Gapmentioning

confidence: 99%

“…Due to the lack of sufficient training data, a flexible posterior approximation can lead the recognition network to reduce the overall inference gap but also over-fit to the training data. Zhang et al (2022) proposed a self-consistent training method wherein a mixture of samples from the training data set and those generated by the generative model were fed to the recognition network during the training phase. This mixture of distributions could be interpreted as a form of training data augmentation to help overcome the over-fitting caused by the application of amortized inference (Zhang et al, 2022).…”

Section: Generalization Gapmentioning

confidence: 99%

See 2 more Smart Citations

Amortized Variational Inference: A Systematic Review

Ganguly,

Jain,

Watchareeruetai

2023

jair

View full text Add to dashboard Cite

The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be faster than several sampling-based techniques. However, the traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points without re-running the optimization process. Recent developments in the field, like stochastic-, black box-, and amortized-VI, have helped address these issues. Generative modeling tasks nowadays widely make use of amortized VI for its efficiency and scalability, as it utilizes a parameterized function to learn the approximate posterior density parameters. In this paper, we review the mathematical foundations of various VI techniques to form the basis for understanding amortized VI. Additionally, we provide an overview of the recent trends that address several issues of amortized VI, such as the amortization gap, generalization issues, inconsistent representation learning, and posterior collapse. Finally, we analyze alternate divergence measures that improve VI optimization.

show abstract

Section: Generalization Gapmentioning

confidence: 99%

Section: Generalization Gapmentioning

confidence: 99%

Section: Generalization Gapmentioning

confidence: 99%

See 1 more Smart Citation

Amortized Variational Inference: A Systematic Review

Ganguly,

Jain,

Watchareeruetai

2023

jair

View full text Add to dashboard Cite

show abstract

“…Expanding the training dataset is a common approach [17][18][19][20][21]. On the other hand, the transfer learning-based methods [22][23][24] and meta-learning methods [25,26] are also effective strategies. While the methods mentioned above can address the issue of scarce data, they are unable to recognize the unseen class targets that lack any training data.…”

Section: Introductionmentioning

confidence: 99%

Zero-Shot SAR Target Recognition Based on a Conditional Generative Network with Category Features from Simulated Images

Chen,

Zhang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

SAR image target recognition relies heavily on a large number of annotated samples, making it difficult to classify the unseen class targets. Due to the lack of effective category auxiliary information, the current zero-shot target recognition methods for SAR images are limited to inferring only one unseen class rather than classifying multiple unseen classes. To address this issue, a conditional generative network with the category features from the simulated images for zero-shot SAR target recognition is proposed in this paper. Firstly, the deep features are extracted from the simulated images and fused into the category features that characterize the entire class. Then, a conditional VAE-GAN network is constructed to generate the feature instances of the unseen classes. The high-level semantic information shared in the category features aids in generalizing the mapping learned from the seen classes to the unseen classes. Finally, the generated features of the unseen classes are used to train a classifier that can classify the real unseen images. The classification accuracies for the targets of the three unseen classes based on the proposed method can reach 99.80 ± 1.22% and 71.57 ± 2.28% with the SAMPLE dataset and the MSTAR dataset, respectively. The advantage and validity of the proposed architecture are indicated with a small number of the seen classes and a small amount of the training data. Furthermore, the proposed method can be extended to generalized zero-shot recognition.

show abstract

“…Thanks to a large number of collected SAR images, automatic target recognition (ATR) of SAR images have attracted increasing popularity in recent years. SAR ATR provides the basis of the reconnaissance of interested regions or the precise strike of threatening targets for both civil and military applications [ 7 , 8 , 9 ]. A commonly used scheme of SAR ATR proposed by the Lincoln laboratory mainly consists of three consecutive stages, which are detection, discrimination, and classification, respectively [ 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion

Liu

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

For target detection in complex scenes of synthetic aperture radar (SAR) images, the false alarms in the land areas are hard to eliminate, especially for the ones near the coastline. Focusing on the problem, an algorithm based on the fusion of multiscale superpixel segmentations is proposed in this paper. Firstly, the SAR images are partitioned by using different scales of superpixel segmentation. For the superpixels in each scale, the land-sea segmentation is achieved by judging their statistical properties. Then, the land-sea segmentation results obtained in each scale are combined with the result of the constant false alarm rate (CFAR) detector to eliminate the false alarms located on the land areas of the SAR image. In the end, to enhance the robustness of the proposed algorithm, the detection results obtained in different scales are fused together to realize the final target detection. Experimental results on real SAR images have verified the effectiveness of the proposed algorithm.

show abstract

SAR Target Recognition via Meta-Learning and Amortized Variational Inference

Cited by 8 publications

References 32 publications

Amortized Variational Inference: A Systematic Review

Amortized Variational Inference: A Systematic Review

Zero-Shot SAR Target Recognition Based on a Conditional Generative Network with Category Features from Simulated Images

Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion

Contact Info

Product

Resources

About