Multimodal 3D Few-Shot Classification via Gaussian Mixture Discriminant Analysis

Simple item page
dc.contributor.authorWu, Yiqien_US
dc.contributor.authorWu, Huachaoen_US
dc.contributor.authorHu, Rongleien_US
dc.contributor.authorChen, Yilinen_US
dc.contributor.authorZhang, Dejunen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:03:24Z
dc.date.available2025-10-07T05:03:24Z
dc.date.issued2025
dc.description.abstractWhile pre-trained 3D vision-language models are becoming increasingly available, there remains a lack of frameworks that can effectively harness their capabilities for few-shot classification. In this work, we propose PointGMDA, a training-free framework that combines Gaussian Mixture Models (GMMs) with Gaussian Discriminant Analysis (GDA) to perform robust classification using only a few labeled point cloud samples. Our method estimatesGMMparameters per class from support data and computes mixture-weighted prototypes, which are then used in GDA with a shared covariance matrix to construct decision boundaries. This formulation allows us to model intra-class variability more expressively than traditional single-prototype approaches, while maintaining analytical tractability. To incorporate semantic priors, we integrate CLIP-style textual prompts and fuse predictions from geometric and textual modalities through a hybrid scoring strategy. We further introduce PointGMDA-T, a lightweight attention-guided refinement module that learns residuals for fast feature adaptation, improving robustness under distribution shift. Extensive experiments on ModelNet40 and ScanObjectNN demonstrate that PointGMDA outperforms strong baselines across a variety of few-shot settings, with consistent gains under both training-free and fine-tuned conditions. These results highlight the effectiveness and generality of our probabilistic modeling and multimodal adaptation framework. Our code is publicly available at https://github.com/djzgroup/PointGMDA.en_US
dc.description.number7
dc.description.sectionheadersCreating and Processing Point Clouds
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70268
dc.identifier.issn1467-8659
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70268
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70268
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Computer graphics; 3D imaging; Computer vision; Machine learning
dc.subjectComputing methodologies → Computer graphics
dc.subject3D imaging
dc.subjectComputer vision
dc.subjectMachine learning
dc.titleMultimodal 3D Few-Shot Classification via Gaussian Mixture Discriminant Analysisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70268.pdf
Size:
4.52 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 7