提出DAP-MAE，提升跨域点云学习效果
DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
- 设计异构域适配器，分预训练与微调阶段自适应融合多域点云知识
- 在ScanObjectNN上达95.18%分类准确率，在Bosphorus上达88.45%表情识别率
- 适用于多域点云分析任务，尤其适合数据稀缺场景
相较于2D数据，不同领域可用于训练的点云数据规模有限。研究人员尝试将多领域数据结合用于掩码自编码器（MAE）预训练，以缓解数据稀缺问题。然而，混合领域先验知识可能与下游3D点云分析任务不匹配，导致性能下降。为此，我们提出域自适应点云掩码自编码器（DAP-MAE），一种用于通用点云分析的MAE预训练方法。DAP-MAE设计了异构域适配器，在预训练阶段采用适配模式，使模型全面学习跨域点云信息；在微调阶段采用融合模式，增强点云特征表示。同时，引入域特征生成器，指导点云特征适配下游任务。仅需一次预训练，DAP-MAE在四个不同点云分析任务中均表现优异，在ScanObjectNN上达到95.18%的物体分类准确率，在Bosphorus上实现88.45%的面部表情识别准确率。
原文摘要 · Abstract (English)
Compared to 2D data, the scale of point cloud data in different domains available for training, is quite limited. Researchers have been trying to combine these data of different domains for masked autoencoder (MAE) pre-training to leverage such a data scarcity issue. However, the prior knowledge learned from mixed domains may not align well with the downstream 3D point cloud analysis tasks, leading to degraded performance. To address such an issue, we propose the Domain-Adaptive Point Cloud Masked Autoencoder (DAP-MAE), an MAE pre-training method, to adaptively integrate the knowledge of cross-domain datasets for general point cloud analysis. In DAP-MAE, we design a heterogeneous domain adapter that utilizes an adaptation mode during pre-training, enabling the model to comprehensively learn information from point clouds across different domains, while employing a fusion mode in the fine-tuning to enhance point cloud features. Meanwhile, DAP-MAE incorporates a domain feature generator to guide the adaptation of point cloud features to various downstream tasks. With only one pre-training, DAP-MAE achieves excellent performance across four different point cloud analysis tasks, reaching 95.18% in object classification on ScanObjectNN and 88.45% in facial expression recognition on Bosphorus.
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。