From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6415-6423
DOI: 10.1609/aaai.v40i8.37569 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Shuangzhi Li und 3 weiteren Autor:innen.
Abstract (Originalsprache)
LiDAR-based 3D object detection models often struggle to generalize to real-world environments due to limited object diversity in existing datasets. To tackle it, we introduce the first generalized cross-domain few-shot (GCFS) task in 3D object detection, aiming to adapt a source-pretrained model to both common and novel classes in a new domain with only few-shot annotations. We propose a unified framework that learns stable target semantics under limited supervision by bridging 2D open-set semantics with 3D spatial reasoning. Specifically, an image-guided multi-modal fusion injects transferable 2D semantic cues into the 3D pipeline via vision-language models, while a physically-aware box search enhances 2D-to-3D alignment via LiDAR priors. To capture class-specific semantics from sparse data, we further introduce contrastive-enhanced prototype learning, which encodes few-shot instances into discriminative semantic anchors and stabilizes representation learning. Extensive experiments on GCFS benchmarks demonstrate the effectiveness and generality of our approach in realistic deployment settings.
Zitieren
APA
Li, S., Shen, J., Ma, L., & Li, X. (2026). From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6415-6423. https://doi.org/10.1609/aaai.v40i8.37569
Vancouver
Li S, Shen J, Ma L, Li X. From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6415-6423. doi:10.1609/aaai.v40i8.37569
BibTeX
@article{Li2026,
author = {Li, Shuangzhi and Shen, Junlong and Ma, Lei and Li, Xingyu},
title = {From Dataset to Real-world: General 3D Object Detection via Generalized Cross-domain Few-shot Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {8},
pages = {6415--6423},
doi = {10.1609/aaai.v40i8.37569}
}
EUVIMED