论文标题
使用对抗训练提高医学成像诊断的可解释性
Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training
论文作者
论文摘要
我们研究了对抗性训练对卷积神经网络（CNN）的解释性的影响，该影响专门用于诊断皮肤癌。我们表明，受对抗训练的CNN的基于梯度的显着性图明显更清晰，并且在视觉上比经过标准训练的CNN的显着相干。此外，我们表明，经过对抗训练的网络突出显示了病变内具有显着颜色变化的区域，这是黑色素瘤的常见特征。我们发现，以较小的学习率进行微调的稳健网络进一步提高了显着性图的清晰度。最后，我们提供了初步工作，这表明鲁棒化的第一层以提取强大的低水平特征导致视觉上一致的解释。
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer. We show that gradient-based saliency maps of adversarially trained CNNs are significantly sharper and more visually coherent than those of standardly trained CNNs. Furthermore, we show that adversarially trained networks highlight regions with significant color variation within the lesion, a common characteristic of melanoma. We find that fine-tuning a robust network with a small learning rate further improves saliency maps' sharpness. Lastly, we provide preliminary work suggesting that robustifying the first layers to extract robust low-level features leads to visually coherent explanations.
