We lifted 6 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| fabio-deep/Variational-Capsule-Routing | canonical | 3 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| evaluate | Ran | fabio-deep/Variational-Capsule-Routing/src/evaluate.py code served (permissive licence) · get_code("077ff9d535eedac5") |
| random_split | Ran | fabio-deep/Variational-Capsule-Routing/src/utils.py code served (permissive licence) · get_code("f484dcb8254eac93") |
| sample_weights | Ran | fabio-deep/Variational-Capsule-Routing/src/utils.py code served (permissive licence) · get_code("9fd2858cfe4e2c4b") |
| mnist | Not yet run | fabio-deep/Variational-Capsule-Routing/src/datasets.py code served (permissive licence) · get_code("65225c611576fdeb") |
| smallnorb | Not yet run | fabio-deep/Variational-Capsule-Routing/src/datasets.py code served (permissive licence) · get_code("6b6b37fba1870426") |
| svhn | Not yet run | fabio-deep/Variational-Capsule-Routing/src/datasets.py code served (permissive licence) · get_code("e91e3ad8e59a43fb") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Capsule networks are a recently proposed type of neural network shown to outperform alternatives in challenging shape recognition tasks. In capsule networks, scalar neurons are replaced with capsule vectors or matrices, whose entries represent different properties of objects. The relationships between objects and their parts are learned via trainable viewpoint-invariant transformation matrices, and the presence of a given object is decided by the level of agreement among votes from its parts. This interaction occurs between capsule layers and is a process called routing-by-agreement. In this paper, we propose a new capsule routing algorithm derived from Variational Bayes for fitting a mixture of transforming gaussians, and show it is possible transform our capsule network into a Capsule-VAE. Our Bayesian approach addresses some of the inherent weaknesses of MLE based models such as the variance-collapse by modelling uncertainty over capsule pose parameters. We outperform the state-of-the-art on smallNORB using 50% fewer capsules than previously reported, achieve competitive performances on CIFAR-10, Fashion-MNIST, SVHN, and demonstrate significant improvement in MNIST to affNIST generalisation over previous works.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1905.11455")
get_code_for_paper("1905.11455")
have("1905.11455")
Connect an agent — have() is free.