Name
Abstract | ||
|---|---|---|
A capsule is a group of neurons whose activity vector models different properties of the same entity. This paper extends the capsule to a generative version, named variational capsules (VCs). Each VC produces a latent variable for a specific entity, making it possible to integrate image analysis and image synthesis into a unified framework. Variational capsules model an image as a composition of entities in a probabilistic model. Different capsulesu0027 divergence with a specific prior distribution represents the presence of different entities, which can be applied in image analysis tasks such as classification. In addition, variational capsules encode multiple entities in a semantically-disentangling way. Diverse instantiations of capsules are related to various properties of the same entity, making it easy to generate diverse samples with fine-grained semantic attributes. Extensive experiments demonstrate that deep networks designed with variational capsules can not only achieve promising performance on image analysis tasks (including image classification and attribute prediction) but can also improve the diversity and controllability of image synthesis. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | ENCODE,Pattern recognition,Controllability,Computer science,Latent variable,Image synthesis,Artificial intelligence,Statistical model,Generative grammar,Prior probability,Contextual image classification,Machine learning |
DocType | Volume | Citations |
Journal | abs/1807.04099 | 1 |
PageRank | References | Authors |
0.34 | 11 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Huang, Huaibo | 1 | 29 | 10.81 |
| Lingxiao Song | 2 | 67 | 5.55 |
| Ran He | 3 | 1790 | 108.39 |
| Zhenan Sun | 4 | 2379 | 139.49 |
| Tieniu Tan | 5 | 11681 | 744.35 |