Sparse Unsupervised Capsules Generalize Better

2018-04-17 · David Rawlinson, Abdelrahman Ahmed, Gideon Kowadlo

We show that unsupervised training of latent capsule layers using only the reconstruction loss, without masking to select the correct output class, causes a loss of equivariances and other desirable capsule qualities. This implies that supervised capsules networks can't be very deep. Unsupervised sparsening of latent capsule layer activity both restores these qualities and appears to generalize better than supervised masking, while potentially enabling deeper capsules networks. We train a sparse, unsupervised capsules network of similar geometry to Sabour et al (2017) on MNIST, and then test classification accuracy on affNIST using an SVM layer. Accuracy is improved from benchmark 79% to 90%.

📄 PDF Abstract BibTeX arXiv:1804.06094

Code (1)

ProjectAGI/sparse-unsupervised-capsules 공식 구현 tf

Tasks

General Classification

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Quaternion Capsule Networks

2020-07-08 · Barış Özcan, Furkan Kınlı, Furkan Kıraç

Capsules are grouping of neurons that allow to represent sophisticated information of a visual entity such as pose and features. In the view of this property, Capsule Networks outperform CNNs in challenging tasks like ob…

Benchmarking Object Recognition

Decoder image-classification Image Classification Unsupervised Image Classification

Sparse Unsupervised Capsules Generalize Better

Code (1)

Tasks

Methods 이 논문이 사용한 방법론

Similar Papers 제목 키워드 기반

Quaternion Capsule Networks

HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network

Training products of expert capsules with mixing by dynamic routing

Neural Network Encapsulation

Unsupervised part representation by Flow Capsules