The Multi-Lane Capsule Network

We introduce multi-lane capsule networks (MLCN), which are a separable and resource efficient organization of capsule networks (CapsNet) that allows parallel processing while achieving high accuracy at reduced cost. A MLCN is composed of a number of (distinct) parallel lanes, each contributing to a dimension of the result, trained using the routing-by-agreement organization of CapsNet. Our results indicate similar accuracy with a much-reduced cost in number of parameters for the Fashion-MNIST and Cifar10 datasets. They also indicate that the MLCN outperforms the original CapsNet when using a proposed novel configuration for the lanes. MLCN also has faster training and inference times, being more than two-fold faster than the original CapsNet in a same accelerator.

[1]  Chen Xu,et al.  MS-CapsNet: A Novel Multi-Scale Capsule Network , 2018, IEEE Signal Processing Letters.

[2]  Mohammed Amer,et al.  Path Capsule Networks , 2020, Neural Processing Letters.

[3]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[4]  Rinat Mukhometzianov,et al.  CapsNet comparative performance evaluation for image classification , 2018, ArXiv.

[5]  Peng Wang,et al.  A Capsule Network for Traffic Speed Prediction in Complex Road Networks , 2018, 2018 Sensor Data Fusion: Trends, Solutions, Applications (SDF).

[6]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[7]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[8]  Premkumar Natarajan,et al.  CapsuleGAN: Generative Adversarial Capsule Network , 2018, ECCV Workshops.

[9]  Geoffrey E. Hinton,et al.  Transforming Autoencoders , 2011 .

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Hong Lu,et al.  Compositional coding capsule network with k-means routing for text classification , 2018, Pattern Recognit. Lett..

[12]  Geoffrey E. Hinton,et al.  Transforming Auto-Encoders , 2011, ICANN.

[13]  Shadi Albarqouni,et al.  Capsule Networks against Medical Imaging Data Challenges , 2018, CVII-STENT/LABELS@MICCAI.

[14]  Konstantinos N. Plataniotis,et al.  IMPROVED EXPLAINABILITY OF CAPSULE NETWORKS: RELEVANCE PATH BY AGREEMENT , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[15]  Hien Van Nguyen,et al.  Fast CapsNet for Lung Cancer Screening , 2018, MICCAI.