$\beta$-CapsNet: Learning Disentangled Representation for CapsNet by Information Bottleneck

• URL: http://arxiv.org/abs/2209.05239v1
• Date: Mon, 12 Sep 2022 13:34:34 GMT
• Title: $\beta$-CapsNet: Learning Disentangled Representation for CapsNet by Information Bottleneck
• Authors: Ming-fei Hu, Jian-wei Liu
• Abstract summary: We present a framework for learning disentangled representation of CapsNet by information bottleneck constraint. Our framework achieves state-of-the-art disentanglement performance compared to CapsNet.
• Score: 3.0437362638485994
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a framework for learning disentangled representation of CapsNet by information bottleneck constraint that distills information into a compact form and motivates to learn an interpretable factorized capsule. In our $\beta$-CapsNet framework, hyperparameter $\beta$ is utilized to trade-off disentanglement and other tasks, variational inference is utilized to convert the information bottleneck term into a KL divergence that is approximated as a constraint on the mean of the capsule. For supervised learning, class independent mask vector is used for understanding the types of variations synthetically irrespective of the image class, we carry out extensive quantitative and qualitative experiments by tuning the parameter $\beta$ to figure out the relationship between disentanglement, reconstruction and classfication performance. Furthermore, the unsupervised $\beta$-CapsNet and the corresponding dynamic routing algorithm is proposed for learning disentangled capsule in an unsupervised manner, extensive empirical evaluations suggest that our $\beta$-CapsNet achieves state-of-the-art disentanglement performance compared to CapsNet and various baselines on several complex datasets both in supervision and unsupervised scenes.

Related papers

• 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)
• RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks [11.302789770501303]
  Capsule Networks (CapsNets) are able to hierarchically preserve the pose relationships between multiple objects for image classification tasks. In this paper, we evaluate different factors affecting the robustness of CapsNets, compared to traditional Conal Neural Networks (CNNs)
  arXiv  Detail & Related papers  (2023-04-08T09:58:35Z)
• Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation [69.0695698566235]
  We study reinforcement learning with linear function approximation and adversarially changing cost functions. We present a computationally efficient policy optimization algorithm for the challenging general setting of unknown dynamics and bandit feedback.
  arXiv  Detail & Related papers  (2023-01-30T17:26:39Z)
• Caption supervision enables robust learners [24.936204628969623]
  We show that CNNs trained on a standard cross-entropy loss can also benefit from caption supervision, in some cases even more than VL models, on the same data. To facilitate future experiments with high-accuracy caption-supervised models, we introduce CaptionNet. In a series of experiments on CaptionNet, we show how the choice of loss function, data filtration and supervision strategy enable robust computer vision.
  arXiv  Detail & Related papers  (2022-10-13T22:29:10Z)
• Hybrid Gromov-Wasserstein Embedding for Capsule Learning [24.520120182880333]
  Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and their relations using a two-step process. hierarchical relationship modeling is computationally expensive, which has limited the wider use of CapsNet despite its potential advantages. We present an efficient approach for learning capsules that surpasses canonical baseline models and even demonstrates superior performance compared to high-performing convolution models.
  arXiv  Detail & Related papers  (2022-09-01T05:26:32Z)
• Routing with Self-Attention for Multimodal Capsule Networks [108.85007719132618]
  We present a new multimodal capsule network that allows us to leverage the strength of capsules in the context of a multimodal learning framework. To adapt the capsules to large-scale input data, we propose a novel routing by self-attention mechanism that selects relevant capsules. This allows not only for robust training with noisy video data, but also to scale up the size of the capsule network compared to traditional routing methods.
  arXiv  Detail & Related papers  (2021-12-01T19:01:26Z)
• FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition [22.712379018181398]
  Capsule networks (CapsNets) have recently shown promise to excel in most computer vision tasks. We propose a CapsNet-based architecture, termed FlowCaps, which attempts to achieve better correspondence matching via finer-grained, motion-specific, and more-interpretable encoding.
  arXiv  Detail & Related papers  (2020-11-08T11:35:08Z)
• Information Obfuscation of Graph Neural Networks [96.8421624921384]
  We study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data. We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance.
  arXiv  Detail & Related papers  (2020-09-28T17:55:04Z)
• 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)
• Budget Learning via Bracketing [50.085728094234476]
  The budget learning problem poses the learner's goal as minimising use of the cloud while suffering no discernible loss in accuracy. We propose a new formulation for the BL problem via the concept of bracketings. We empirically validate our theory on real-world datasets, demonstrating improved performance over prior gating based methods.
  arXiv  Detail & Related papers  (2020-04-14T04:38:14Z)
• A Theory of Usable Information Under Computational Constraints [103.5901638681034]
  We propose a new framework for reasoning about information in complex systems. Our foundation is based on a variational extension of Shannon's information theory. We show that by incorporating computational constraints, $mathcalV$-information can be reliably estimated from data.
  arXiv  Detail & Related papers  (2020-02-25T06:09:30Z)
• CoLES: Contrastive Learning for Event Sequences with Self-Supervision [63.3568071938238]
  We address the problem of self-supervised learning on discrete event sequences generated by real-world users. We propose a new method "CoLES", which adapts contrastive learning, previously used for audio and computer vision domains.
  arXiv  Detail & Related papers  (2020-02-19T15:15:57Z)
• 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)
• Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning [59.65752299209042]
  We investigate learning a ConvNet under such a scenario. We found that a ConvNet significantly over-fits the minor classes. We propose to incorporate class-dependent temperatures (CDT) training ConvNet.
  arXiv  Detail & Related papers  (2020-01-06T03:52:11Z)

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.