Timezone: »

Canonical Capsules: Self-Supervised Capsules in Canonical Pose
Weiwei Sun · Andrea Tagliasacchi · Boyang Deng · Sara Sabour · Soroosh Yazdani · Geoffrey Hinton · Kwang Moo Yi

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @

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.

Author Information

Weiwei Sun (University of British Columbia)
Andrea Tagliasacchi (Google Research, Brain)
Boyang Deng (Waymo LLC)
Sara Sabour (Google)
Soroosh Yazdani (Google Canada)
Geoffrey Hinton (Google)
Kwang Moo Yi (The University of British Columbia)

More from the Same Authors