PrunedCaps: A Case For Primary Capsules Discrimination
Capsule Networks (CapsNets) are a generation of image classifiers with proven advantages over Convolutional Neural Networks (CNNs). Better robustness to affine transformation and overlapping image detection are some of the benefits associated with CapsNets. However, CapsNets cannot be classified as resource-efficient deep learning architecture due to the high number of Primary Capsules (PCs). In addition, CapsNets' training and testing are slow and resource hungry. This paper investigates the possibility of Primary Capsules pruning in CapsNets on MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and SVHN datasets. We show that a pruned version of CapsNet performs up to 9.90 times faster than the conventional architecture by removing 95 percent of Capsules without a loss of accuracy. Also, our pruned architecture saves on more than 95.36 percent of floating-point operations in the dynamic routing stage of the architecture. Moreover, we provide insight into why some datasets benefit significantly from pruning while others fall behind.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Dynamic Routing on Deep Neural Network for Thoracic Disease Classification and Sensitive Area Localization
We present and evaluate a new deep neural network architecture for automatic thoracic disease detection on chest X-rays. Deep neural networks have shown great success in a plethora of visual recognition tasks such as ima…
General Classificationimage-classificationImage Classificationobject-detection+2Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical improvement method
Capsule network has shown various advantages over convolutional neural network (CNN). It keeps more precise spatial information than CNN and uses equivariance instead of invariance during inference and highly potential t…
Hierarchical Object-Centric Learning with Capsule Networks
Capsule networks (CapsNets) were introduced to address convolutional neural networks limitations, learning object-centric representations that are more robust, pose-aware, and interpretable. They organize neurons into gr…
Computational EfficiencyLung Nodule SegmentationObjectEmploying Deep Part-Object Relationships for Salient Object Detection
Despite Convolutional Neural Networks (CNNs) based methods have been successful in detecting salient objects, their underlying mechanism that decides the salient intensity of each image part separately cannot avoid incon…
Objectobject-detectionObject DetectionRGB Salient Object Detection+1Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection
The part-whole relational property endowed by Capsule Networks (CapsNets) has been known successful for camouflaged object detection due to its segmentation integrity. However, the previous Expectation Maximization (EM) …
Mambaobject-detectionObject Detection