Attention mechanisms are critically important in the advancement of synthetic aperture radar (SAR) automatic target recognition (ATR) systems. Traditional SAR ATR models often struggle with the noisy nature of the SAR data, frequently learning from background noise rather than the most relevant image features. Attention mechanisms address this limitation by focusing on crucial image components, such as the shadows and small parts of a vehicle, which are crucial for accurate target classification. By dynamically prioritizing these significant features, attention-based models can efficiently characterize the entire image with a few pixels, thus enhancing recognition performance. This capability allows for the discrimination of targets from background clutter, leading to more practical and robust SAR ATR models. We show that attention modules increase top-1 accuracy, improve input robustness, and are qualitatively more explainable on the MSTAR dataset.

The analytical performance has the size of the model, the number of parameters, the number of I.

In recent years, deep learning has been widely used in SAR ATR and achieved excellent performance on the MSTAR dataset. However, due to constrained imaging conditions, MSTAR has data biases such as background correlation, i.e., background clutter properties have a spurious correlation with target classes. Deep learning can overfit clutter to reduce training errors. Therefore, the degree of overfitting for clutter reflects the non-causality of deep learning in SAR ATR. Existing methods only qualitatively analyze this phenomenon. In this paper, we quantify the contributions of different regions to target recognition based on the Shapley value. The Shapley value of clutter measures the degree of overfitting. Moreover, we explain how data bias and model bias contribute to non-causality. Concisely, data bias leads to comparable signal-to-clutter ratios and clutter textures in training and test sets. And various model structures have different degrees of overfitting for these biases. The experimental results of various models under standard operating conditions on the MSTAR dataset support our conclusions. Our code is available at https://github.com/waterdisappear/Data-Bias-in-MSTAR.

With the present revival of interest in bistatic radar systems, research in that area has gained momentum. Given some of the strategic advantages for a bistatic configuration, and tech- nological advances in the past few years, large-scale implementation of the bistatic systems is a scope for the near future. If the bistatic systems are to replace the monostatic systems (at least par- tially), then all the existing usages of a monostatic system should be manageable in a bistatic system. A detailed investigation of the possibilities of an automatic target recognition (ATR) facil- ity in a bistatic radar system is presented. Because of the lack of data, experiments were carried out on simulated data. Still, the results are positive and make a positive case for the introduction of the bistatic configuration. First, it was found that, contrary to the popular expectation that the bistatic ATR performance might be substantially worse than the monostatic ATR performance, the bistatic ATR performed fairly well (though not better than the monostatic ATR). Second, the ATR per- formance does not deteriorate substantially with increasing bistatic angle. Last, the polarimetric data from bistatic scattering were found to have distinct information, contrary to expert opinions. Along with these results, suggestions were also made about how to stabilise the bistatic-ATR per- formance with changing bistatic angle. Finally, a new fast and robust ATR algorithm (developed in the present work) has been presented.