Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation

Abstract

Invariance against rotations of 3D objects is an important property in analyzing 3D point set data. Conventional 3D point set DNNs having rotation invariance typically obtain accurate 3D shape features via supervised learning by using labeled 3D point sets as training samples. However, due to the rapid increase in 3D point set data and the high cost of labeling, a framework to learn rotation-invariant 3D shape features from numerous unlabeled 3D point sets is required. This paper proposes a novel self-supervised learning framework for acquiring accurate and rotation-invariant 3D point set features at object-level. Our proposed lightweight DNN architecture decomposes an input 3D point set into multiple global-scale regions, called tokens, that preserve the spatial layout of partial shapes composing the 3D object. We employ a self-attention mechanism to refine the tokens and aggregate them into an expressive rotation-invariant feature per 3D point set. Our DNN is effectively trained by using pseudo-labels generated by a self-distillation framework. To facilitate the learning of accurate features, we propose to combine multi-crop and cut-mix data augmentation techniques to diversify 3D point sets for training. Through a comprehensive evaluation, we empirically demonstrate that, (1) existing rotation-invariant DNN architectures designed for supervised learning do not necessarily learn accurate 3D shape features under a self-supervised learning scenario, and (2) our proposed algorithm learns rotation-invariant 3D point set features that are more accurate than those learned by existing algorithms. Code is available at https://github.com/takahikof/RIPT_SDMM

Accepted to the CVIU journal

References in corpus (18)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• A Simple Framework for Contrastive Learning of Visual Representations
• Bootstrap your own latent: A new approach to self-supervised Learning
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• PCT: Point cloud transformer
• Self-Supervised Representation Learning: Introduction, Advances and Challenges
• Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
• Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
• A Rotation-Invariant Framework for Deep Point Cloud Analysis
• Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
• Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud
• Canonical Capsules: Self-Supervised Capsules in Canonical Pose
• Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning
• VN-Transformer: Rotation-Equivariant Attention for Vector Neurons
• DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold