arXiv 2209.052392022-09-12cs.CV

$β$ - CapsNet：利用信息瓶颈学习CapsNet的解纠缠表示

$β$-CapsNet: Learning Disentangled Representation for CapsNet by Information Bottleneck

China University of Petroleum（中国石油大学）

Ming-fei Hu, Jian-wei Liu

备注：: 31 pages

摘要：

我们提出了一个框架，通过信息瓶颈约束，将信息提取成一个紧凑的形式，并激励学习一个可解释的因式分解胶囊的CapsNet学习解纠缠表示。在我们的$β$ -CapsNet框架中，超参数$β$被用来权衡解纠缠和其他任务，变分推理被用来将信息瓶颈项转换为KL散度，该KL散度被近似为对胶囊均值的约束。在监督学习中，使用类无关掩码向量来综合理解图像的变化类型，通过调整参数$β$，进行了大量的定量和定性实验，研究了去纠缠、重构和分类性能之间的关系。此外，无监督的$β$ -CapsNet和相应的动态路由算法，提出了学习解开胶囊在无监督的方式，广泛的实证评估表明，我们的$β$ -CapsNet实现了最先进的解开性能相比，CapsNet和各种基线的几个复杂的数据集，无论是在监督和无监督的场景。

英文摘要：

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 $β$-CapsNet framework, hyperparameter $β$ 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 $β$ to figure out the relationship between disentanglement, reconstruction and classfication performance. Furthermore, the unsupervised $β$-CapsNet and the corresponding dynamic routing algorithm is proposed for learning disentangled capsule in an unsupervised manner, extensive empirical evaluations suggest that our $β$-CapsNet achieves state-of-the-art disentanglement performance compared to CapsNet and various baselines on several complex datasets both in supervision and unsupervised scenes.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文