Canonical Capsules: Unsupervised Capsules in Canonical Pose

• URL: http://arxiv.org/abs/2012.04718v1
• Date: Tue, 8 Dec 2020 20:13:28 GMT
• Title: Canonical Capsules: Unsupervised Capsules in Canonical Pose
• Authors: Weiwei Sun, Andrea Tagliasacchi, Boyang Deng, Sara Sabour, Soroosh Yazdani, Geoffrey Hinton, Kwang Moo Yi
• Abstract summary: We propose an unsupervised 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. By learning an object-centric representation in an unsupervised manner, our method outperforms the state-of-the-art on 3D point cloud reconstruction, registration, and unsupervised classification.
• Score: 31.529908150084626
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose an unsupervised 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. In doing so, we require neither classification labels nor manually-aligned training datasets to train. Yet, by learning an object-centric representation in an unsupervised manner, our method outperforms the state-of-the-art on 3D point cloud reconstruction, registration, and unsupervised classification. We will release the code and dataset to reproduce our results as soon as the paper is published.

Related papers

• The Triad of Failure Modes and a Possible Way Out [7.977229957867868]
  We present a novel objective function for cluster-based self-supervised learning (SSL) that is designed to circumvent the triad of failure modes. This objective consists of three key components: (i) A generative term that penalizes representation collapse, (ii) a term that promotes invariance to data augmentations, and (ii) a uniformity term that penalizes cluster collapse.
  arXiv  Detail & Related papers  (2023-09-27T05:54:14Z)
• Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images [133.68032636906133]
  We study the problem of estimating 3D shape and pose of an object in terms of keypoints, from a single 2D image. The shape and pose are learned directly from images collected by categories and their partial 2D keypoint annotations.
  arXiv  Detail & Related papers  (2022-11-14T16:18:11Z)
• Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding [61.30276576646909]
  We propose an augmentation-free unsupervised approach for point clouds to learn transferable point-level features via soft clustering, named SoftClu. We exploit the affiliation of points to their clusters as a proxy to enable self-training through a pseudo-label prediction task.
  arXiv  Detail & Related papers  (2022-10-06T10:18:16Z)
• Self-Supervised Point Cloud Representation Learning with Occlusion Auto-Encoder [63.77257588569852]
  We present 3D Occlusion Auto-Encoder (3D-OAE) for learning representations for point clouds. Our key idea is to randomly occlude some local patches of the input point cloud and establish the supervision via recovering the occluded patches. In contrast with previous methods, our 3D-OAE can remove a large proportion of patches and predict them only with a small number of visible patches.
  arXiv  Detail & Related papers  (2022-03-26T14:06:29Z)
• ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes [55.689763519293464]
  ConDor is a self-supervised method that learns to canonicalize the 3D orientation and position for full and partial 3D point clouds. During inference, our method takes an unseen full or partial 3D point cloud at an arbitrary pose and outputs an equivariant canonical pose.
  arXiv  Detail & Related papers  (2022-01-19T18:57:21Z)
• Unsupervised Representation Learning for 3D Point Cloud Data [66.92077180228634]
  We propose a simple yet effective approach for unsupervised point cloud learning. In particular, we identify a very useful transformation which generates a good contrastive version of an original point cloud. We conduct experiments on three downstream tasks which are 3D object classification, shape part segmentation and scene segmentation.
  arXiv  Detail & Related papers  (2021-10-13T10:52:45Z)
• Learning 3D Dense Correspondence via Canonical Point Autoencoder [108.20735652143787]
  We propose a canonical point autoencoder (CPAE) that predicts dense correspondences between 3D shapes of the same category. The autoencoder performs two key functions: (a) encoding an arbitrarily ordered point cloud to a canonical primitive, and (b) decoding the primitive back to the original input instance shape.
  arXiv  Detail & Related papers  (2021-07-10T15:54:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.