Timezone: »

Capsule Networks: A Generative Probabilistic Perspective
Lewis Smith
Event URL: https://slideslive.com/38930870/capsule-networks-a-generative-probabilistic-perspective »

`Capsule' models try to explicitly represent the poses of objects, enforcing a linear relationship between an objects pose and those of its constituent parts. This modelling assumption should lead to robustness to viewpoint changes since the object-component relationships are invariant to the poses of the object. We describe a probabilistic generative model that encodes these assumptions. Our probabilistic formulation separates the generative assumptions of the model from the inference scheme, which we derive from a variational bound. We experimentally demonstrate the applicability of our unified objective, and the use of test time optimisation to solve problems inherent to amortised inference.

Author Information

Lewis Smith (University of Oxford)

Lewis smith is a DPhil student in Yarin Gals OATML lab at the University of Oxford, in the third year of his studies. Before that he did an undergraduate in Physics at the university of Manchester. His interests are in probabilistic methods, and in particular in structured methods that build in assumptions appropriate to the problem, such as object factorisation or assumptions about invariances.

More from the Same Authors