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

• URL: http://arxiv.org/abs/2510.21635v1
• Date: Fri, 24 Oct 2025 16:44:40 GMT
• Title: DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
• Authors: Ziqi Gao, Qiufu Li, Linlin Shen,
• Abstract summary: We propose Domain-Adaptive Point Cloud Masked Autoencoder (DAP-MAE), an MAE pre-training method.<n>DAP-MAE incorporates a domain feature generator to guide the adaptation of point cloud features to various downstream tasks.<n>With only one pre-training, DAP-MAE achieves excellent performance across four different point cloud analysis tasks.
• Score: 56.86793222623566
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• MSCN: Multi-view Structural Convolution Network for Domain-Invariant Point Cloud Recognition of Autonomous Vehicles [1.7616042687330637]
  Multi-view Structural Convolution Network (MSCN) is a novel architecture designed to achieve domain-invariant recognition.<n>MSCN consistently outperforms state-of-the-art point cloud classification methods across all domain change scenarios.
  arXiv  Detail & Related papers  (2025-01-27T18:25:35Z)
• Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images [22.054023867495722]
  Cloud segmentation is a critical challenge in remote sensing image interpretation. We present a parameter-efficient adaptive approach, termed Cloud-Adapter, to enhance the accuracy and robustness of cloud segmentation.
  arXiv  Detail & Related papers  (2024-11-20T08:37:39Z)
• PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Model [77.00221501105788]
  Domain Generalization (DG) has been recently explored to improve the generalizability of point cloud classification.<n>We present the first work that studies the generalizability of state space models (SSMs) in DG PCC.<n>We propose a novel framework, PointDGMamba, that excels in strong generalizability toward unseen domains.
  arXiv  Detail & Related papers  (2024-08-24T12:53:48Z)
• Point Cloud Mamba: Point Cloud Learning via State Space Model [73.7454734756626]
  We show that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs) In particular, we demonstrate that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs) Point Cloud Mamba surpasses the state-of-the-art (SOTA) point-based method PointNeXt and achieves new SOTA performance on the ScanNN, ModelNet40, ShapeNetPart, and S3DIS datasets.
  arXiv  Detail & Related papers  (2024-03-01T18:59:03Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation [65.78246406460305]
  compositional semantic mixing represents the first unsupervised domain adaptation technique for point cloud segmentation. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world)
  arXiv  Detail & Related papers  (2023-08-28T14:43:36Z)
• PointPatchMix: Point Cloud Mixing with Patch Scoring [58.58535918705736]
  We propose PointPatchMix, which mixes point clouds at the patch level and generates content-based targets for mixed point clouds. Our approach preserves local features at the patch level, while the patch scoring module assigns targets based on the content-based significance score from a pre-trained teacher model. With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86.3% accuracy on ScanObjectNN and 94.1% accuracy on ModelNet40.
  arXiv  Detail & Related papers  (2023-03-12T14:49:42Z)
• Self-Distillation for Unsupervised 3D Domain Adaptation [15.660045080090711]
  We propose an Unsupervised Domain Adaptation (UDA) method for point cloud classification in 3D vision. In this work, we focus on obtaining a discriminative feature space for the target domain enforcing consistency between a point cloud and its augmented version. We propose a novel iterative self-training methodology that exploits Graph Neural Networks in the UDA context to refine pseudo-labels.
  arXiv  Detail & Related papers  (2022-10-15T08:37:02Z)
• A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds [7.731213699116179]
  We propose a learnable self-supervised task and integrate it into a self-supervision-based point cloud UDA architecture. In the UDA architecture, an encoder is shared between the networks for the self-supervised task and the main task of point cloud classification or segmentation. Experiments on PointDA-10 and PointSegDA datasets show that the proposed method achieves new state-of-the-art performance on both classification and segmentation tasks of point cloud UDA.
  arXiv  Detail & Related papers  (2021-04-12T02:30:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.