可视化和改进散射网络
Visualizing and Improving Scattering Networks
摘要：
由Mallat引入的散射变换（或散射网）是创建用于模式识别和图像分类任务的定义良好的特征提取器的一个有希望的开始。由于它们与卷积神经网络（CNN）的结构相似，它们特别令人感兴趣，同时不需要参数学习并且仍然表现得非常好（特别是在约束分类任务中）。在本文中，我们可视化了ScatterNet的深层对使用“DeScatterNet”敏感。我们发现，更高的订单ScatterNets是敏感的复杂的，边缘样的模式（棋盘和波纹边缘）。这些复杂的模式可能对纹理分类有用，但与卷积神经网络（CNN）的第二层和第三层中可视化的模式非常不同-当前最先进的图像分类器。我们认为这可能是ScatterNets和CNN之间当前性能差距的来源（ScatterNet+SVM与ResNet在CIFAR-10上的83%与93%）。然后，我们使用这些可视化工具对ScatterNet设计提出可能的增强，这表明它们有能力提取更接近CNN的特征，同时仍然定义良好，并具有ScatterNet的基本不变性。
英文摘要：
Scattering Transforms (or ScatterNets) introduced by Mallat are a promising start into creating a well-defined feature extractor to use for pattern recognition and image classification tasks. They are of particular interest due to their architectural similarity to Convolutional Neural Networks (CNNs), while requiring no parameter learning and still performing very well (particularly in constrained classification tasks). In this paper we visualize what the deeper layers of a ScatterNet are sensitive to using a 'DeScatterNet'. We show that the higher orders of ScatterNets are sensitive to complex, edge-like patterns (checker-boards and rippled edges). These complex patterns may be useful for texture classification, but are quite dissimilar from the patterns visualized in second and third layers of Convolutional Neural Networks (CNNs) - the current state of the art Image Classifiers. We propose that this may be the source of the current gaps in performance between ScatterNets and CNNs (83% vs 93% on CIFAR-10 for ScatterNet+SVM vs ResNet). We then use these visualization tools to propose possible enhancements to the ScatterNet design, which show they have the power to extract features more closely resembling CNNs, while still being well-defined and having the invariance properties fundamental to ScatterNets.
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。
