Self-distillation for Efficient Object-level Point Cloud Learning

Simple item page
dc.contributor.authorOyarzún, Lucasen_US
dc.contributor.authorSipiran, Ivanen_US
dc.contributor.authorSaavedra, José M.en_US
dc.contributor.editorBiasotti, Silviaen_US
dc.contributor.editorBustos, Benjaminen_US
dc.contributor.editorSchreck, Tobiasen_US
dc.contributor.editorSipiran, Ivanen_US
dc.contributor.editorVeltkamp, Remco C.en_US
dc.date.accessioned2024-08-20T08:25:22Z
dc.date.available2024-08-20T08:25:22Z
dc.date.issued2024
dc.description.abstractThe emerging accessibility of 3D point cloud data has catalyzed the evolution of deep-learning methodologies for analysis and processing of 3D data. However, the efficacy of neural networks in this domain is often inhibited by the necessity for extensively labelled datasets. In this study, we investigate the application of self-distillation techniques based on Siamese networks, BYOL and SIMSIAM, to pre-train encoders designed for 3D point cloud processing. These pre-training regimes enable encoders to generate data representations without label reliance, potentially supporting network performance in downstream tasks. The efficacy of these learned representations was assessed using the established evaluation methodologies for pre-training: linear probing and finetuning. We also incorporate an analysis of self-supervised features in a retrieval scenario. Furthermore, the impact of these representations on subsequent applications was evaluated via transfer learning by employing pre-trained models as a foundation for standard test datasets.en_US
dc.description.sectionheadersShort Papers
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.identifier.doi10.2312/3dor.20241174
dc.identifier.isbn978-3-03868-242-4
dc.identifier.issn1997-0471
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.2312/3dor.20241174
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/3dor20241174
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Point-based models; Shape analysis; Shape representations
dc.subjectComputing methodologies → Point based models
dc.subjectShape analysis
dc.subjectShape representations
dc.titleSelf-distillation for Efficient Object-level Point Cloud Learningen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
3dor20241174.pdf
Size:
963.42 KB
Format:
Adobe Portable Document Format
Download
Collections
3DOR 2024 - Short Papers