iCaps: An Interpretable Classifier via Disentangled Capsule Networks

• URL: http://arxiv.org/abs/2008.08756v1
• Date: Thu, 20 Aug 2020 03:44:26 GMT
• Title: iCaps: An Interpretable Classifier via Disentangled Capsule Networks
• Authors: Dahuin Jung, Jonghyun Lee, Jihun Yi, and Sungroh Yoon
• Abstract summary: We propose an interpretable Capsule Network, iCaps, for image classification. iCaps provides a prediction along with clear rationales behind it with no performance degradation.
• Score: 25.052072276266912
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an interpretable Capsule Network, iCaps, for image classification. A capsule is a group of neurons nested inside each layer, and the one in the last layer is called a class capsule, which is a vector whose norm indicates a predicted probability for the class. Using the class capsule, existing Capsule Networks already provide some level of interpretability. However, there are two limitations which degrade its interpretability: 1) the class capsule also includes classification-irrelevant information, and 2) entities represented by the class capsule overlap. In this work, we address these two limitations using a novel class-supervised disentanglement algorithm and an additional regularizer, respectively. Through quantitative and qualitative evaluations on three datasets, we demonstrate that the resulting classifier, iCaps, provides a prediction along with clear rationales behind it with no performance degradation.

Related papers

• ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis [6.273401483558281]
  This paper introduces a novel capsule network, ParseCaps, which utilizes the sparse axial attention routing and parse convolutional capsule layer to form a parse-tree-like structure. Experimental results on CE-MRI, PH$2$, and Derm7pt datasets show that ParseCaps not only outperforms other capsule network variants in classification accuracy, redundancy reduction and robustness, but also provides interpretable explanations.
  arXiv  Detail & Related papers  (2024-11-03T13:34:31Z)
• Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection [98.6460229237143]
  We propose a novel mamba capsule routing at the type level. These type-level mamba capsules are fed into the EM routing algorithm to get the high-layer mamba capsules. On top of that, to retrieve the pixel-level capsule features for further camouflaged prediction, we achieve this on the basis of the low-layer pixel-level capsules.
  arXiv  Detail & Related papers  (2024-10-05T00:20:22Z)
• Hierarchical Object-Centric Learning with Capsule Networks [0.0]
  Capsule networks (CapsNets) were introduced to address convolutional neural networks limitations. This thesis investigates the intriguing aspects of CapsNets and focuses on three key questions to unlock their full potential.
  arXiv  Detail & Related papers  (2024-05-30T09:10:33Z)
• Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning [120.53458753007851]
  Few-shot class-incremental learning (FSCIL) has been a challenging problem as only a few training samples are accessible for each novel class in the new sessions. We deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse. We propose a neural collapse inspired framework for FSCIL. Experiments on the miniImageNet, CUB-200, and CIFAR-100 datasets demonstrate that our proposed framework outperforms the state-of-the-art performances.
  arXiv  Detail & Related papers  (2023-02-06T18:39:40Z)
• HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network [76.92310948325847]
  We propose a Hierarchical Parsing Capsule Network (HP-Capsule) for unsupervised face subpart-part discovery. HP-Capsule extends the application of capsule networks from digits to human faces and takes a step forward to show how the neural networks understand objects without human intervention.
  arXiv  Detail & Related papers  (2022-03-21T01:39:41Z)
• Capsule networks with non-iterative cluster routing [2.8935588665357077]
  In existing routing procedures, capsules produce predictions (termed votes) for capsules of the next layer. In the proposed cluster routing, capsules produce vote clusters instead of individual votes for next-layer capsules. The proposed capsule networks achieve the best accuracy on the Fashion-MNIST and SVHN datasets with fewer parameters.
  arXiv  Detail & Related papers  (2021-09-19T20:14:22Z)
• Conditional Variational Capsule Network for Open Set Recognition [64.18600886936557]
  In open set recognition, a classifier has to detect unknown classes that are not known at training time. Recently proposed Capsule Networks have shown to outperform alternatives in many fields, particularly in image recognition. In our proposal, during training, capsules features of the same known class are encouraged to match a pre-defined gaussian, one for each class.
  arXiv  Detail & Related papers  (2021-04-19T09:39:30Z)
• A Novel BGCapsule Network for Text Classification [5.010425616264462]
  We propose a novel hybrid architecture viz., BGCapsule, which is a Capsule model preceded by an ensemble of Bidirectional Gated Recurrent Units (BiGRU) for several text classification tasks. BGCapsule achieves better accuracy compared to the existing methods without the help of any external linguistic knowledge.
  arXiv  Detail & Related papers  (2020-07-02T06:07:29Z)
• Linguistically Driven Graph Capsule Network for Visual Question Reasoning [153.76012414126643]
  We propose a hierarchical compositional reasoning model called the "Linguistically driven Graph Capsule Network" The compositional process is guided by the linguistic parse tree. Specifically, we bind each capsule in the lowest layer to bridge the linguistic embedding of a single word in the original question with visual evidence. Experiments on the CLEVR dataset, CLEVR compositional generation test, and FigureQA dataset demonstrate the effectiveness and composition generalization ability of our end-to-end model.
  arXiv  Detail & Related papers  (2020-03-23T03:34:25Z)
• 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)

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.