DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Ziqi, Li, Qiufu, Shen, Linlin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912669092544512
author Gao, Ziqi
Li, Qiufu
Shen, Linlin
author_facet Gao, Ziqi
Li, Qiufu
Shen, Linlin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21635
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
Gao, Ziqi
Li, Qiufu
Shen, Linlin
Computer Vision and Pattern Recognition
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.
title DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.21635