paper-with-me

홈 › Papers

Routing Towards Discriminative Power of Class Capsules

2021-03-07 · HaoYu Yang, Shuhe Li, Bei Yu

Capsule networks are recently proposed as an alternative to modern neural network architectures. Neurons are replaced with capsule units that represent specific features or entities with normalized vectors or matrices. The activation of lower layer capsules affects the behavior of the following capsules via routing links that are constructed during training via certain routing algorithms. We discuss the routing-by-agreement scheme in dynamic routing algorithm which, in certain cases, leads the networks away from optimality. To obtain better and faster convergence, we propose a routing algorithm that incorporates a regularized quadratic programming problem which can be solved efficiently. Particularly, the proposed routing algorithm targets directly on the discriminative power of class capsules making the correct decision on input instances. We conduct experiments on MNIST, MNIST-Fashion, and CIFAR-10 and show competitive classification results compared to existing capsule networks.

📄 PDF Abstract BibTeX arXiv:2103.04278

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Hyperbolic Capsule Networks for Multi-Label Classification

2020-07-01 · ACL 2020 6 · Boli Chen, Xin Huang, Lin Xiao, Liping Jing

Although deep neural networks are effective at extracting high-level features, classification methods usually encode an input into a vector representation via simple feature aggregation operations (e.g. pooling). Such op…

ClassificationGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Graph Routing between Capsules

2021-06-22 · Yang Li, Wei Zhao, Erik Cambria, Suhang Wang 외

Routing methods in capsule networks often learn a hierarchical relationship for capsules in successive layers, but the intra-relation between capsules in the same layer is less studied, while this intra-relation is a key…

Relationtext-classificationText Classification

Using dynamic routing to extract intermediate features for developing scalable capsule networks

2019-07-13 · Bodhisatwa Mandal, Swarnendu Ghosh, Ritesh Sarkhel, Nibaran Das 외

Capsule networks have gained a lot of popularity in short time due to its unique approach to model equivariant class specific properties as capsules from images. However the dynamic routing algorithm comes with a steep c…

Capsules with Inverted Dot-Product Attention Routing

2020-02-12 · ICLR 2020 1 · Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov

We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote. The new mechanism 1) designs routing via …

Image Classification

STAR-Caps: Capsule Networks with Straight-Through Attentive Routing

2019-12-01 · NeurIPS 2019 12 · Karim Ahmed, Lorenzo Torresani

Capsule networks have been shown to be powerful models for image classification, thanks to their ability to represent and capture viewpoint variations of an object. However, the high computational complexity of capsule n…

ClassificationGeneral Classificationimage-classificationImage Classification