Open Long-Tailed Multimodal 3D Model Classification Based on Sample-Enhanced Category-Space Learning
Journal of Imaging · 10.08.2026 · 12 (8) · 370
DOI: 10.3390/jimaging12080370 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 10.08.2026. Verfasst von Yuansa Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Heilongjiang Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
With the rapid development of three-dimensional (3D) sensing technologies, multimodal 3D model classification has achieved significant progress. However, most existing methods are developed under closed and balanced assumptions, which limits their applicability to open long-tailed scenarios with scarce tail classes, ambiguous hard samples, and continuously emerging categories. In this work, we propose sample-enhanced category-space learning (SE-CSL) for open long-tailed multimodal 3D model classification. The proposed method first uses dual-branch modality encoders to extract point-cloud structural representations and multi-view semantic representations. Mamba is then introduced to model global dependencies across heterogeneous modalities and generate a unified global category representation. To improve the robustness of category representation, we design a category-space learning strategy that jointly integrates long-tailed learning, few-shot representation stabilization, and hard-sample enhancement. A long-tail balanced loss, a few-shot stabilization loss, and a hard-sample boundary loss are further developed to optimize intra-class compactness, inter-class separability, and boundary discrimination. To handle continually emerging classes, we introduce an incremental category-space expansion mechanism that distinguishes new classes, preserves old-class information, and supports unified classification of old and new categories. Extensive experiments on ModelNet40 and ShapeNet55 demonstrate the effectiveness and robustness of SE-CSL.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China.
- Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China.
Förderung
- Heilongjiang Provincial Natural Science Foundation of China
Zitieren
APA
Wang, Y., Gao, X., Zhang, C., & Xue, Y. (2026). Open Long-Tailed Multimodal 3D Model Classification Based on Sample-Enhanced Category-Space Learning. Journal of Imaging, 12(8), 370. https://doi.org/10.3390/jimaging12080370
Vancouver
Wang Y, Gao X, Zhang C, Xue Y. Open Long-Tailed Multimodal 3D Model Classification Based on Sample-Enhanced Category-Space Learning. Journal of Imaging. 2026;12(8):370. doi:10.3390/jimaging12080370
BibTeX
@article{Wang2026,
author = {Wang, Yuansa and Gao, Xueyao and Zhang, Chunxiang and Xue, Yongzeng},
title = {Open Long-Tailed Multimodal 3D Model Classification Based on Sample-Enhanced Category-Space Learning},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {8},
pages = {370},
doi = {10.3390/jimaging12080370}
}
EUVIMED