Semantics-Augmented Quantization-Aware Training for Point Cloud Classification

Simple item page
dc.contributor.authorHuang, Limingen_US
dc.contributor.authorQin, Yunchuanen_US
dc.contributor.authorLi, Ruihuien_US
dc.contributor.authorWu, Fanen_US
dc.contributor.authorLi, Kenlien_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:03:06Z
dc.date.available2024-10-13T18:03:06Z
dc.date.issued2024
dc.description.abstractPoint cloud classification is a pivotal procedure in 3D computer vision, and its deployment in practical applications is often constrained by limited computational and memory resources. To address these issues, we introduce a Semantics-Augmented Quantization-Aware Training (SAQAT) framework designed for efficient and precise classification of point cloud data. The SAQAT framework incorporates a point importance prediction semantic module as a side output, which assists in identifying crucial points, along with a point importance evaluation algorithm (PIEA). The semantics module leverages point importance prediction to skillfully select quantization levels based on local geometric properties and semantic context. This approach reduces errors by retaining essential information. In synergy, the PIEA acts as the cornerstone, providing an additional layer of refinement to SAQAT framework. Furthermore, we integrates a loss function that mitigates classification loss, quantization error, and point importance prediction loss, thereby fostering a reliable representation of the quantized data. The SAQAT framework is designed for seamless integration with existing point cloud models, enhancing their efficiency while maintaining high levels of accuracy. Testing on benchmark datasets demonstrates that our SAQAT framework surpasses contemporary quantization methods in classification accuracy while simultaneously economizing on memory and computational resources. Given these advantages, our SAQAT framework holds enormous potential for a wide spectrum of applications within the rapidly evolving domain of 3D computer vision. Our code is released: https://github.com/h-liming/SAQAT.en_US
dc.description.sectionheadersPoint Cloud Processing and Analysis I
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241275
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241275
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241275
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 → Object recognition
dc.subjectComputing methodologies → Object recognition
dc.titleSemantics-Augmented Quantization-Aware Training for Point Cloud Classificationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20241275.pdf
Size:
848.78 KB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters