提出EPContrast，让大点云理解更高效
EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding
- 分粒度嵌入构建正负样本对，降低计算开销
- 通道特征图间对比提升模型泛化能力
- 标签少、训练一周期仍表现优异，适合小数据场景
通过点级对比学习获取归纳偏置在点云预训练中至关重要。然而，点云规模增大时计算需求呈平方增长，严重制约实际部署。为此，本文提出面向大规模点云理解的有效点级对比学习方法EPContrast，包含AGContrast与ChannelContrast两部分。AGContrast基于非对称粒度嵌入构建正负样本对，ChannelContrast在通道特征图间施加对比监督。EPContrast在保持点级对比损失的同时显著降低计算负担。在S3DIS和ScanNetV2上全面验证，涵盖语义分割、实例分割与目标检测任务。丰富的消融实验表明，在标签效率低和单周期训练设置下仍具备出色的偏置诱导能力。
原文摘要 · Abstract (English)
The acquisition of inductive bias through point-level contrastive learning holds paramount significance in point cloud pre-training. However, the square growth in computational requirements with the scale of the point cloud poses a substantial impediment to the practical deployment and execution. To address this challenge, this paper proposes an Effective Point-level Contrastive Learning method for large-scale point cloud understanding dubbed \textbf{EPContrast}, which consists of AGContrast and ChannelContrast. In practice, AGContrast constructs positive and negative pairs based on asymmetric granularity embedding, while ChannelContrast imposes contrastive supervision between channel feature maps. EPContrast offers point-level contrastive loss while concurrently mitigating the computational resource burden. The efficacy of EPContrast is substantiated through comprehensive validation on S3DIS and ScanNetV2, encompassing tasks such as semantic segmentation, instance segmentation, and object detection. In addition, rich ablation experiments demonstrate remarkable bias induction capabilities under label-efficient and one-epoch training settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。