PrunedCaps: A Case For Primary Capsules Discrimination

• URL: http://arxiv.org/abs/2512.06003v1
• Date: Tue, 02 Dec 2025 04:31:58 GMT
• Title: PrunedCaps: A Case For Primary Capsules Discrimination
• Authors: Ramin Sharifi, Pouya Shiri, Amirali Baniasadi,
• Abstract summary: We show that a pruned version of CapsNet performs up to 9.90 times faster than the conventional architecture.<n>Our pruned architecture saves on more than 95.36 percent of floating-point operations in the dynamic routing stage of the architecture.
• Score: 0.06372261626436675
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• DL-CapsNet: A Deep and Light Capsule Network [0.07161783472741746]
  We propose a deep variant of CapsNet consisting of several capsule layers.<n>DL-CapsNet, while being highly accurate, employs a small number of parameters and delivers faster training and inference.
  arXiv  Detail & Related papers  (2025-11-23T05:45:11Z)
• LE-CapsNet: A Light and Enhanced Capsule Network [0.07161783472741746]
  Capsule Network (CapsNet) has several advantages over CNNs.<n>CapsNet is slow due to its different structure.<n>We propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet.
  arXiv  Detail & Related papers  (2025-11-12T15:45:48Z)
• Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network [0.07161783472741746]
  We introduce Convolutional Fully-Connected Capsule Network (CFC-CapsNet) to address the shortcomings of CapsNet.<n>CFC-CapsNet produces fewer, yet more powerful capsules resulting in higher network accuracy.<n>Our experiments show that CFC-CapsNet achieves competitive accuracy, faster training and inference.
  arXiv  Detail & Related papers  (2025-11-06T19:27:15Z)
• Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks [53.974190296524455]
  We revisit ChebNet to shed light on its ability to model distant node interactions.<n>We cast ChebNet as a stable and non-dissipative dynamical system, which we coin Stable-ChebNet.
  arXiv  Detail & Related papers  (2025-06-09T10:41:34Z)
• VeCLIP: Improving CLIP Training via Visual-enriched Captions [63.547204530720705]
  This study introduces a scalable pipeline for noisy caption rewriting. We emphasize the incorporation of visual concepts into captions, termed as Visual-enriched Captions (VeCap) We showcase the adaptation of this method for training CLIP on large-scale web-crawled datasets, termed VeCLIP.
  arXiv  Detail & Related papers  (2023-10-11T17:49:13Z)
• Interpretable Graph Capsule Networks for Object Recognition [17.62514568986647]
  We propose interpretable Graph Capsule Networks (GraCapsNets), where we replace the routing part with a multi-head attention-based Graph Pooling approach. GraCapsNets achieve better classification performance with fewer parameters and better adversarial robustness, when compared to CapsNets.
  arXiv  Detail & Related papers  (2020-12-03T03:18:00Z)
• iCapsNets: Towards Interpretable Capsule Networks for Text Classification [95.31786902390438]
  Traditional machine learning methods are easy to interpret but have low accuracies. We propose interpretable capsule networks (iCapsNets) to bridge this gap. iCapsNets can be interpreted both locally and globally.
  arXiv  Detail & Related papers  (2020-05-16T04:11:44Z)
• Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks [12.022910298030219]
  Capsule Networks (CapsNets) have superior learning capabilities in machine learning tasks, like image classification, compared to the traditional CNNs. CapsNets require extremely intense computations and are difficult to be deployed in their original form at the resource-constrained edge devices. This paper makes the first attempt to quantize CapsNet models, to enable their efficient edge implementations, by developing a specialized quantization framework for CapsNets.
  arXiv  Detail & Related papers  (2020-04-15T14:32:45Z)
• Improved Residual Networks for Image and Video Recognition [98.10703825716142]
  Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture. We show consistent improvements in accuracy and learning convergence over the baseline. Our proposed approach allows us to train extremely deep networks, while the baseline shows severe optimization issues.
  arXiv  Detail & Related papers  (2020-04-10T11:09:50Z)
• Subspace Capsule Network [85.69796543499021]
  SubSpace Capsule Network (SCN) exploits the idea of capsule networks to model possible variations in the appearance or implicitly defined properties of an entity. SCN can be applied to both discriminative and generative models without incurring computational overhead compared to CNN during test time.
  arXiv  Detail & Related papers  (2020-02-07T17:51:56Z)
• Convolutional Networks with Dense Connectivity [59.30634544498946]
  We introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks.
  arXiv  Detail & Related papers  (2020-01-08T06:54:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.