paper-with-me

홈 › Papers

P-CapsNets: a General Form of Convolutional Neural Networks

2019-12-18 · Zhenhua Chen, Xiwen Li, Chuhua Wang, David Crandall

We propose Pure CapsNets (P-CapsNets) which is a generation of normal CNNs structurally. Specifically, we make three modifications to current CapsNets. First, we remove routing procedures from CapsNets based on the observation that the coupling coefficients can be learned implicitly. Second, we replace the convolutional layers in CapsNets to improve efficiency. Third, we package the capsules into rank-3 tensors to further improve efficiency. The experiment shows that P-CapsNets achieve better performance than CapsNets with varied routing procedures by using significantly fewer parameters on MNIST\&CIFAR10. The high efficiency of P-CapsNets is even comparable to some deep compressing models. For example, we achieve more than 99\% percent accuracy on MNIST by using only 3888 parameters. We visualize the capsules as well as the corresponding correlation matrix to show a possible way of initializing CapsNets in the future. We also explore the adversarial robustness of P-CapsNets compared to CNNs.

📄 PDF Abstract BibTeX arXiv:1912.08367

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessForm

Similar Papers 제목 키워드 기반

Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification

2019-01-29 · Hao Ren, Jianlin Su, Hong Lu

Image classification is a challenging problem which aims to identify the category of object in the image. In recent years, deep Convolutional Neural Networks (CNNs) have been applied to handle this task, and impressive i…

ClassificationGeneral Classificationimage-classificationImage Classification

Improving the Robustness of Capsule Networks to Image Affine Transformations

2019-11-18 · CVPR 2020 6 · Jindong Gu, Volker Tresp

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 extr…

RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks

2023-04-08 · Alberto Marchisio, Antonio De Marco, Alessio Colucci, Maurizio Martina 외

Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. Other than achieving high accuracy, another relevant factor in deploying Cap…

image-classificationImage Classification

Interpretable Graph Capsule Networks for Object Recognition

2020-12-03 · Jindong Gu, Volker Tresp

Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create e…

Adversarial RobustnessObjectObject Recognition

Effective and Efficient Vote Attack on Capsule Networks

2021-02-19 · ICLR 2021 1 · Jindong Gu, Baoyuan Wu, Volker Tresp

Standard Convolutional Neural Networks (CNNs) can be easily fooled by images with small quasi-imperceptible artificial perturbations. As alternatives to CNNs, the recently proposed Capsule Networks (CapsNets) are shown t…

Adversarial Robustness