LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
- URL: http://arxiv.org/abs/2405.17149v1
- Date: Mon, 27 May 2024 13:19:23 GMT
- Title: LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
- Authors: Yaohua Zha, Naiqi Li, Yanzi Wang, Tao Dai, Hang Guo, Bin Chen, Zhi Wang, Zhihao Ouyang, Shu-Tao Xia,
- Abstract summary: We propose a locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder.
Our results show that our compact model significantly surpasses existing Transformer-based models in both performance and efficiency.
- Score: 47.94285833315427
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transformer, leading to quadratic complexity and limited decoder, hindering their practice application. To address this limitation, we first conduct a comprehensive analysis of existing Transformer-based MPM, emphasizing the idea that redundancy reduction is crucial for point cloud analysis. To this end, we propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. Considering the varying information density between masked and unmasked patches in the decoder inputs of MPM, we introduce a locally constrained Mamba-based decoder. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density. Extensive experimental results show that our compact model significantly surpasses existing Transformer-based models in both performance and efficiency, especially our LCM-based Point-MAE model, compared to the Transformer-based model, achieved an improvement of 2.24%, 0.87%, and 0.94% in performance on the three variants of ScanObjectNN while reducing parameters by 88% and computation by 73%.
Related papers
- Pre-training Point Cloud Compact Model with Partial-aware Reconstruction [51.403810709250024]
We present a pre-trained Point cloud Compact Model with Partial-aware textbfReconstruction, named Point-CPR.
Our model exhibits strong performance across various tasks, especially surpassing the leading MPM-based model PointGPT-B with only 2% of its parameters.
arXiv Detail & Related papers (2024-07-12T15:18:14Z) - Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning [116.75939193785143]
Contrastive learning (CL) for Vision Transformers (ViTs) in image domains has achieved performance comparable to CL for traditional convolutional backbones.
In 3D point cloud pretraining with ViTs, masked autoencoder (MAE) modeling remains dominant.
arXiv Detail & Related papers (2024-07-08T12:28:56Z) - Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model [18.30032389736101]
Mamba model, based on state space models (SSM), outperforms Transformer in multiple areas with only linear complexity.
We present Mamba3D, a state space model tailored for point cloud learning to enhance local feature extraction.
arXiv Detail & Related papers (2024-04-23T12:20:27Z) - SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation [53.675725490807615]
We introduce SDPose, a new self-distillation method for improving the performance of small transformer-based models.
SDPose-T obtains 69.7% mAP with 4.4M parameters and 1.8 GFLOPs, while SDPose-S-V2 obtains 73.5% mAP on the MSCOCO validation dataset.
arXiv Detail & Related papers (2024-04-04T15:23:14Z) - Point Cloud Mamba: Point Cloud Learning via State Space Model [64.85865751243448]
This research focuses on applying such architecture in point cloud analysis.
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 ScanObjectNN, ModelNet40, ShapeNetPart, and S3DIS datasets.
arXiv Detail & Related papers (2024-03-01T18:59:03Z) - CD-CTFM: A Lightweight CNN-Transformer Network for Remote Sensing Cloud
Detection Fusing Multiscale Features [5.600932842087808]
A lightweight CNN-Transformer network, CD-CTFM, is proposed to solve the problem.
CD-CTFM is based on encoder-decoder architecture and incorporates the attention mechanism.
The proposed model is evaluated on two cloud datasets, 38-Cloud and MODIS.
arXiv Detail & Related papers (2023-06-12T15:37:18Z) - 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)
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.