DECAPS：面向细节的胶囊网络
DECAPS: Detail-Oriented Capsule Networks
摘要：
胶囊网络（CapsNets）已被证明是卷积神经网络（CNN）的一种有前途的替代方案。然而，它们在大规模高维数据集上往往达不到最先进的精度。我们提出了一个面向细节的胶囊网络（DECAPS），它结合了CapsNets的优势和几种新技术，以提高其分类精度。首先，DECAPS使用反向动态路由（IDR）机制将较低级别的胶囊分组到头中，然后将它们发送到较高级别的胶囊。这种策略使胶囊能够选择性地关注数据中的小但信息丰富的细节，这些细节可能在CNN的池化操作期间丢失。第二，DECAPS采用了一个躲猫猫训练程序，它鼓励网络通过第二级注意力计划关注细粒度的信息。最后，蒸馏过程通过对原始和参与的图像区域预测进行平均来提高DECAPS的鲁棒性。我们在CheXpert和RSNA Pneumonia数据集上进行了大量实验，以验证DECAPS的有效性。我们的网络不仅在分类方面实现了最先进的准确性（在CheXpert数据集上将ROC曲线下的平均面积从87.24%提高到92.82%），而且在疾病区域的弱监督定位方面也实现了最先进的准确性（将RSNA Pneumonia检测数据集的平均精度从41.7%提高到80%）。
英文摘要：
Capsule Networks (CapsNets) have demonstrated to be a promising alternative to Convolutional Neural Networks (CNNs). However, they often fall short of state-of-the-art accuracies on large-scale high-dimensional datasets. We propose a Detail-Oriented Capsule Network (DECAPS) that combines the strength of CapsNets with several novel techniques to boost its classification accuracies. First, DECAPS uses an Inverted Dynamic Routing (IDR) mechanism to group lower-level capsules into heads before sending them to higher-level capsules. This strategy enables capsules to selectively attend to small but informative details within the data which may be lost during pooling operations in CNNs. Second, DECAPS employs a Peekaboo training procedure, which encourages the network to focus on fine-grained information through a second-level attention scheme. Finally, the distillation process improves the robustness of DECAPS by averaging over the original and attended image region predictions. We provide extensive experiments on the CheXpert and RSNA Pneumonia datasets to validate the effectiveness of DECAPS. Our networks achieve state-of-the-art accuracies not only in classification (increasing the average area under ROC curves from 87.24% to 92.82% on the CheXpert dataset) but also in the weakly-supervised localization of diseased areas (increasing average precision from 41.7% to 80% for the RSNA Pneumonia detection dataset).
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。
