Push-and-Pull: A General Training Framework With Differential Augmentor for Domain Generalized Point Cloud Classification
- 28 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (8) , 7165-7175
Abstract
As a fundamental task of 3D perception, point cloud recognition has shown significant progress in recent years. However, existing methods still face challenges when dealing with geometry differences, resulting in performance degradation when a distribution gap exists between the training and testing data, also known as domain generalization. In this work, we focus on this problem and propose a general training framework, named Push-and-Pull, aimed at effectively improving the generalization ability of models on unseen target domains. Specifically, our framework first introduces a learnable 3D data augmentor to generate new training point clouds, which helps to reduce the domain bias and enrich the source training set. Also, an adversarial training strategy is proposed to push the augmented samples away from the original ones in the latent space and meanwhile keep the geometric structure. Second, based on the original and augmented samples, a dual-level consistency regularization strategy on logits and feature spaces is designed to pull the deviated representations back to their original space as close as possible, and promote discriminative and domain-agnostic representations. These two steps are iteratively optimized to enhance the overall performance. Extensive experiments on the PointDA-10 and Sim2Real benchmarks consistently demonstrate the effectiveness of our proposed framework.Keywords
Funding Information
- National Natural Science Foundation of China (62071127, 62101137)
- National Key Research and Development Program of China (2022ZD0160100)
- Shanghai Natural Science Foundation (23ZR1402900)
- CFFF Platform of Fudan University
This publication has 35 references indexed in Scilit:
- PointCutMix: Regularization strategy for point cloud classificationNeurocomputing, 2022
- PCT: Point cloud transformerComputational Visual Media, 2021
- PointMixup: Augmentation for Point Clouds2020
- Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition2019
- Learning to Sample2019
- Multi-view Harmonized Bilinear Network for 3D Object Recognition2018
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- OctNet: Learning Deep 3D Representations at High Resolutions2017
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image2017
- 3D ShapeNets: A deep representation for volumetric shapes2015