[论文解读] Improving the Robustness of Capsule Networks to Image Affine Transformations

Jindong Gu, Volker Tresp|arXiv (Cornell University)|Nov 18, 2019

Domain Adaptation and Few-Shot Learning参考文献 26被引用 5

一句话总结

本文提出Aff-CapsNets，一种改进的胶囊网络架构，通过用简单平均代替动态路由，并在主胶囊间应用相同的变换函数，提升了对仿射变换的鲁棒性。在AffNIST基准测试中，Aff-CapsNets实现了93.21%的准确率——显著优于先前最先进方法CapsNet的79%——且无需使用任何路由机制，表明路由并非实现仿射鲁棒性的必要条件。

ABSTRACT

Convolutional neural networks (CNNs) achieve translational invariance by using pooling operations. However, the operations do not preserve the spatial relationships in the learned representations. Hence, CNNs cannot extrapolate to various geometric transformations of inputs. Recently, Capsule Networks (CapsNets) have been proposed to tackle this problem. In CapsNets, each entity is represented by a vector and routed to high-level entity representations by a dynamic routing algorithm. CapsNets have been shown to be more robust than CNNs to affine transformations of inputs. However, there is still a huge gap between their performance on transformed inputs compared to untransformed versions. In this work, we first revisit the routing procedure by (un)rolling its forward and backward passes. Our investigation reveals that the routing procedure contributes neither to the generalization ability nor to the affine robustness of the CapsNets. Furthermore, we explore the limitations of capsule transformations and propose affine CapsNets (Aff-CapsNets), which are more robust to affine transformations. On our benchmark task, where models are trained on the MNIST dataset and tested on the AffNIST dataset, our Aff-CapsNets improve the benchmark performance by a large margin (from 79% to 93.21%), without using any routing mechanism.

研究动机与目标

• 探究胶囊网络中的动态路由是否有助于仿射鲁棒性或泛化能力。
• 识别现有胶囊网络在处理变换输入时性能受限的架构缺陷。
• 设计一种更鲁棒的胶囊网络架构，在不依赖路由机制的前提下，保持在仿射变换下的高性能。
• 证明在几何鲁棒性方面，更简单的架构可优于复杂的路由机制。

提出的方法

• 作者对动态路由过程的前向和反向传播进行展开，以分析其对模型性能的贡献。
• 他们提出Aff-CapsNets，用胶囊输出间的简单平均操作替代动态路由。
• Aff-CapsNets中所有主胶囊均应用相同的变换函数，确保胶囊间特征学习的一致性。
• 该架构在主胶囊间共享权重矩阵，以增强对几何变换的不变性。
• 该方法在标准基准上进行评估：在MNIST上训练，在AffNIST上测试。
• 通过大量消融实验，比较了有路由与无路由，以及不同架构选择对仿射鲁棒性的影响。

实验结果

研究问题

• RQ1 胶囊网络中的动态路由过程是否有助于泛化能力或仿射鲁棒性？
• RQ2 胶囊网络中哪些架构组件限制了其在仿射变换下的性能？
• RQ3 无路由的更简单架构能否在变换数据上实现优于基于路由的胶囊网络的鲁棒性？
• RQ4 动态路由是否为胶囊网络关键优势（如视角不变性或对抗鲁棒性）所必需？

主要发现

• 数值和实证分析表明，动态路由过程既未提升泛化能力，也未增强胶囊网络的仿射鲁棒性。
• 移除路由并用简单平均替代后，AffNIST上的性能从79%提升至93.21%。
• Aff-CapsNets在AffNIST基准上实现了最先进性能，且未使用任何路由机制。
• 在所有主胶囊间使用相同的变换函数显著增强了对仿射变换的鲁棒性。
• 所提出的架构参数量更少，且准确率高于先前的CapsNet变体。
• 结果表明，路由并非实现仿射鲁棒性的必要条件，挑战了路由是胶囊网络优越性的关键这一假设。