Point-AGM : Attention Guided Masked Auto-Encoder for Joint Self-supervised Learning on Point Clouds

Simple item page
dc.contributor.authorLiu, Jieen_US
dc.contributor.authorYang, Mengnaen_US
dc.contributor.authorTian, Yuen_US
dc.contributor.authorLi, Yancuien_US
dc.contributor.authorSong, Daen_US
dc.contributor.authorLi, Kangen_US
dc.contributor.authorCao, Xinen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:08:02Z
dc.date.available2024-10-13T18:08:02Z
dc.date.issued2024
dc.description.abstractMasked point modeling (MPM) has gained considerable attention in self-supervised learning for 3D point clouds. While existing self-supervised methods have progressed in learning from point clouds, we aim to address their limitation of capturing high-level semantics through our novel attention-guided masking framework, Point-AGM. Our approach introduces an attention-guided masking mechanism that selectively masks low-attended regions, enabling the model to concentrate on reconstructing more critical areas and addressing the limitations of random and block masking strategies. Furthermore, we exploit the inherent advantages of the teacher-student network to enable cross-view contrastive learning on augmented dual-view point clouds, enforcing consistency between complete and partially masked views of the same 3D shape in the feature space. This unified framework leverages the complementary strengths of masked point modeling, attention-guided masking, and contrastive learning for robust representation learning. Extensive experiments have shown the effectiveness of our approach and its well-transferable performance across various downstream tasks. Specifically, our model achieves an accuracy of 94.12% on ModelNet40 and 87.16% on the PB-T50-RS setting of ScanObjectNN, outperforming other self-supervised learning methods.en_US
dc.description.number7
dc.description.sectionheadersPoint Cloud Processing and Analysis II
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15219
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15219
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15219
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectKeywords: Point Cloud Processing, Self-Supervised Learning, Self-Distilling, Mask Modeling. CCS Concepts: Computing methodologies → Self-supervised learning; Mathematics of computing → Probability and statistics
dc.subjectPoint Cloud Processing
dc.subjectSelf
dc.subjectSupervised Learning
dc.subjectSelf
dc.subjectDistilling
dc.subjectMask Modeling. CCS Concepts
dc.subjectComputing methodologies → Self
dc.subjectsupervised learning
dc.subjectMathematics of computing → Probability and statistics
dc.titlePoint-AGM : Attention Guided Masked Auto-Encoder for Joint Self-supervised Learning on Point Cloudsen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
cgf15219.pdf
Size:
1.64 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 7