Improving Sar Automatic Target Recognition Using Simulated Images Under Deep Residual Refinements

Cha, Miriam; Majumdar, Arjun; Kung, H. T.; Barber, Jarred

doi:10.1109/icassp.2018.8462109

Cited by 37 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal is to reconcile any differences between the manifolds of the synthetic/measured data by transforming the synthetic data to "look" more like the measured data. This is motivated by the observation that using synthetic data in its unaltered form yields poor performing models in measured data applications [9]. Some methods in this category rely on training DL-based Generative Adversarial Networks (GANs) and/or Auto-Encoders to learn the transform based on seeing many examples of both synthetic and measured data [10], [11], [9].…”

Section: Learning With Synthetic Datamentioning

confidence: 99%

“…This is motivated by the observation that using synthetic data in its unaltered form yields poor performing models in measured data applications [9]. Some methods in this category rely on training DL-based Generative Adversarial Networks (GANs) and/or Auto-Encoders to learn the transform based on seeing many examples of both synthetic and measured data [10], [11], [9]. Further, Scarnati and Lewis [8] design a pre-processing function for synthetic SAMPLE data which performs a de-specking, quantization, and clutter transfer between (measured, synthetic) pairs.…”

Section: Learning With Synthetic Datamentioning

confidence: 99%

See 1 more Smart Citation

Bridging a Gap in SAR-ATR: Training on Fully Synthetic and Testing on Measured Data

Inkawhich

Davis

et al. 2021

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

View full text Add to dashboard Cite

Obtaining measured Synthetic Aperture Radar (SAR) data for training Automatic Target Recognition (ATR) models can be too expensive (in terms of time and money) and complex of a process in many situations. In response, researchers have developed methods for creating synthetic SAR data for targets using electromagnetic prediction software, which is then used to enrich an existing measured training dataset. However, this approach relies on the availability of some amount of measured data. In this work, we focus on the case of having 100% synthetic training data, while testing on only measured data. We use the SAMPLE dataset public released by AFRL, and find significant challenges to learning generalizable representations from the synthetic data due to distributional differences between the two modalities and extremely limited training sample quantities. Using deep learning-based ATR models, we propose data augmentation, model construction, loss function choices, and ensembling techniques to enhance the representation learned from the synthetic data, and ultimately achieved over 95% accuracy on the SAMPLE dataset. We then analyze the functionality of our ATR models using saliency and feature-space investigations and find them to learn a more cohesive representation of the measured and synthetic data. Finally, we evaluate the out-oflibrary detection performance of our synthetic-only models and find that they are nearly 10% more effective than baseline methods at identifying measured test samples that do not belong to the training class set. Overall, our techniques and their compositions significantly enhance the feasibility of using ATR models trained exclusively on synthetic data.

show abstract

Section: Learning With Synthetic Datamentioning

confidence: 99%

Section: Learning With Synthetic Datamentioning

confidence: 99%

Bridging a Gap in SAR-ATR: Training on Fully Synthetic and Testing on Measured Data

Inkawhich

Davis

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…In Ref. 16, when a simulated dataset generated with a point-scattering model for radar image simulation as described by Holtzman et al 17 was mixed with a real dataset, there was a boost in improvement to the accuracy of target recognition in synthetic aperture radar images in ships.…”

Section: Introductionmentioning

confidence: 99%

Defect recognition in line-space patterns aided by deep learning with data augmentation

Ahn

Kim

et al. 2021

J. Micro/Nanopattern. Mats. Metro.

View full text Add to dashboard Cite

Background: Finding optimal processing conditions to reduce defectivity is a major challenge in high-resolution lithographic tools such as directed self-assembly and extreme ultraviolet lithography.Aim: We aim to develop an efficient automated method that can detect defects and identify their types and locations, allowing for assessing the performance of lithographic processing conditions more easily.Approach: We propose a deep learning approach using an object recognition neural network for the classification and detection of defects in scanning electron microscopy (SEM) images featuring line-space patterns. We optimized our network by exploring its design variables and applied it on a case with limited numbers of SEM images available for training the network.Results: With an optimized network and data augmentation strategies (flipping and mixing images from simulations), it was possible to achieve a significant increase in the performance of the network. Transferability of the network was also proven when applied on a more diverse dataset of SEM images gathered from selected publications. Conclusions:The outcome of our work shows that the amalgamation of an optimal network design and augmentation strategies performs satisfactorily for defectivity analysis and is generic for data not constrained to fixed settings.

show abstract

“…CNNs have found application to synthetic aperture radar (SAR) in recent works using datasets such as the publicly available MSTAR dataset [16][17][18][19][20][21]. These studies typically used predefined network architectures that can contain many learnable parameters; other available architectures can contain upwards of a million parameters [22][23][24], which require significant amounts of memory.…”

Section: Introductionmentioning

confidence: 99%

Target Classification in Synthetic Aperture Radar Images Using Quantized Wavelet Scattering Networks

Raj

Fox

Narayanan

2021

Sensors

View full text Add to dashboard Cite

The need to classify targets and features in high-resolution imagery is of interest in applications such as detection of landmines in ground penetrating radar and tumors in medical ultrasound images. Convolutional neural networks (CNNs) trained using extensive datasets are being investigated recently. However, large CNNs and wavelet scattering networks (WSNs), which share similar properties, have extensive memory requirements and are not readily extendable to other datasets and architectures—and especially in the context of adaptive and online learning. In this paper, we quantitatively study several quantization schemes on WSNs designed for target classification using X-band synthetic aperture radar (SAR) data and investigate their robustness to low signal-to-noise ratio (SNR) levels. A detailed study was conducted on the tradeoffs involved between the various quantization schemes and the means of maximizing classification performance for each case. Thus, the WSN-based quantization studies performed in this investigation provide a good benchmark and important guidance for the design of quantized neural networks architectures for target classification.

show abstract

Improving Sar Automatic Target Recognition Using Simulated Images Under Deep Residual Refinements

Cited by 37 publications

References 8 publications

Bridging a Gap in SAR-ATR: Training on Fully Synthetic and Testing on Measured Data

Bridging a Gap in SAR-ATR: Training on Fully Synthetic and Testing on Measured Data

Defect recognition in line-space patterns aided by deep learning with data augmentation

Target Classification in Synthetic Aperture Radar Images Using Quantized Wavelet Scattering Networks

Contact Info

Product

Resources

About