基于深度学习的压缩感知鲁棒性度量
Measuring Robustness in Deep Learning Based Compressive Sensing
摘要：
深度神经网络提供了最先进的准确性，可以从少量和嘈杂的测量中重建图像，这是加速磁共振成像（MRI）中出现的一个问题。然而，最近的工作引起了人们的担忧，即基于深度学习的图像重建方法对扰动敏感，并且不如传统方法鲁棒：神经网络（i）可能对小的但不利的扰动敏感，（ii）可能在分布偏移下表现不佳，（iii）可能无法恢复图像中小但重要的特征。为了了解这种扰动的敏感性，在这项工作中，我们测量的鲁棒性的不同方法的图像重建，包括训练和未训练的神经网络以及传统的基于稀疏性的方法。我们发现，与以前的作品相反，训练和未训练的方法都容易受到对抗性扰动的影响。此外，针对特定数据集调整的训练和未训练方法都受到分布偏移的影响。最后，我们证明了一个图像重建方法，实现更高的重建质量，也表现出更好的精确恢复细节。我们的结果表明，最先进的基于深度学习的图像重建方法比传统方法提供了更好的性能，而不影响鲁棒性。
英文摘要：
Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive to perturbations and are less robust than traditional methods: Neural networks (i) may be sensitive to small, yet adversarially-selected perturbations, (ii) may perform poorly under distribution shifts, and (iii) may fail to recover small but important features in an image. In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods. We find, contrary to prior works, that both trained and un-trained methods are vulnerable to adversarial perturbations. Moreover, both trained and un-trained methods tuned for a particular dataset suffer very similarly from distribution shifts. Finally, we demonstrate that an image reconstruction method that achieves higher reconstruction quality, also performs better in terms of accurately recovering fine details. Our results indicate that the state-of-the-art deep-learning-based image reconstruction methods provide improved performance than traditional methods without compromising robustness.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
