paper-with-me

홈 › Papers

How to Accelerate Capsule Convolutions in Capsule Networks

2021-04-06 · Zhenhua Chen, Xiwen Li, Qian Lou, David Crandall

How to improve the efficiency of routing procedures in CapsNets has been studied a lot. However, the efficiency of capsule convolutions has largely been neglected. Capsule convolution, which uses capsules rather than neurons as the basic computation unit, makes it incompatible with current deep learning frameworks' optimization solution. As a result, capsule convolutions are usually very slow with these frameworks. We observe that capsule convolutions can be considered as the operations of `multiplication of multiple small matrics' plus tensor-based combination. Based on this observation, we develop two acceleration schemes with CUDA APIs and test them on a custom CapsNet. The result shows that our solution achieves a 4X acceleration.

📄 PDF Abstract BibTeX arXiv:2104.02621

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Building Deep Equivariant Capsule Networks

2020-05-01 · ICLR 2020 1 · Sai Raam Venkataraman, S. Balasubramanian, R. Raghunatha Sarma

Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule networks that aims to remedy this. We identi…

Building Deep, Equivariant Capsule Networks

2019-08-04 · Sairaam Venkatraman, S. Balasubramanian, R. Raghunatha Sarma

Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule networks that aims to remedy this. We identi…

Iterative collaborative routing among equivariant capsules for transformation-robust capsule networks

2022-10-20 · Sai Raam Venkataraman, S. Balasubramanian, R. Raghunatha Sarma

Transformation-robustness is an important feature for machine learning models that perform image classification. Many methods aim to bestow this property to models by the use of data augmentation strategies, while more f…

Data Augmentationimage-classificationImage Classification

Single Image Super-Resolution Based on Capsule Neural Networks

2022-10-06 · George Corrêa de Araújo, Helio Pedrini

Single image super-resolution (SISR) is the process of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the r…

image-classificationImage Super-ResolutionSuper-Resolution

Retinal Vessel Segmentation with Deep Graph and Capsule Reasoning

2024-09-17 · Xinxu Wei, Xi Lin, Haiyun Liu, Shixuan Zhao 외

Effective retinal vessel segmentation requires a sophisticated integration of global contextual awareness and local vessel continuity. To address this challenge, we propose the Graph Capsule Convolution Network (GCC-UNet…

Graph AttentionImage SegmentationMedical Image SegmentationRetinal Vessel Segmentation+2