Geoffrey Hinton, Kwang Moo, Weiwei Sun, Andrea Tagliasacchi, Boyang Deng, Sara Sabour, Soroosh Yazdani
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule decompositions of objects through permutation-equivariant attention, and self-supervise the process by training with pairs of randomly rotated objects. Our key idea is to aggregate the attention masks into semantic keypoints, and use these to supervise a decomposition that satisfies the capsule invariance/equivariance properties. This not only enables the training of a semantically consistent decomposition, but also allows us to learn a canonicalization operation that enables object-centric reasoning. To train our neural network we require neither classification labels nor manually-aligned training datasets. Yet, by learning an object-centric representation in a self-supervised manner, our method outperforms the state-of-the-art on 3D point cloud reconstruction, canonicalization, and unsupervised classification.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.04718")
get_code_for_paper("2012.04718")
have("2012.04718")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.04718.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.04718)
Connect an agent — have() is free.