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.
翻译:Translated abstract:
近年来,深度学习在SAR目标识别中得到了广泛应用并在MSTAR数据集上取得了出色的表现。然而,由于成像条件受限,MSTAR存在数据偏差,如背景相关性,即背景杂波属性具有与目标类别的虚假关联。深度学习可以过拟合杂波以减少训练误差。因此,过拟合程度反映了深度学习在SAR目标识别中的非因果性。现有方法只是定性分析该现象。在本文中,我们基于Shapley值量化不同区域对目标识别的贡献。杂波的Shapley值衡量了过拟合程度。此外,我们解释了数据偏差和模型偏差如何导致非因果性。简而言之,数据偏差导致训练集和测试集中的信杂比和杂波纹理可比。而不同的模型结构对这些偏差有不同的过拟合程度。在MSTAR数据集标准操作条件下,各种模型的实验结果支持了我们的结论。我们的代码可从https://github.com/waterdisappear/Data-Bias-in-MSTAR 获取。