Routing Towards Discriminative Power of Class Capsules
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hyperbolic Capsule Networks for Multi-Label Classification
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-ClASSIFICATIONGraph Routing between Capsules
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 ClassificationUsing dynamic routing to extract intermediate features for developing scalable capsule networks
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
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 ClassificationSTAR-Caps: Capsule Networks with Straight-Through Attentive Routing
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