EUVIMEDEUVIMED entdecken
Crossref

Less Is Better: Sparse Instance Learning for Cross-Domain Few-Shot Object Detection

Yali Huang, Jie Mei, Ziyi Wu, Yiming Yang, Hongru Zhao, Mingyuan Jiu, Hichem Sahbi

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5176-5184

DOI: 10.1609/aaai.v40i7.37432 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yali Huang und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-Domain Few-Shot Object Detection (CD-FSOD) is an extremely challenging task due to the inherent data scarcity and substantial domain shift between the source and target domains. Existing methods often suffer from overfitting and noisy feature representations, which hinder the construction of discriminative class prototypes in the target domain. In this paper, we propose a novel framework with sparse instance learning (SI-ViTO) for CD-FSOD, which leverages instance sparsity to achieve a better detection with less representation. SI-ViTO adopts a dual-stage sparsity module, consisting of instance feature sparsity not only on the few-shot support images but also on the query images. This dual sparsity enables the model to effectively preserve salient foreground semantics and simultaneously to filter out redundant or noisy information. Furthermore, a new prototype calibration strategy is also used to dynamically refine the class prototypes with query instances to accelerate prototype adaptation. Extensive experimental results on CD-FSOD benchmarks show that SI-ViTO outperforms the state-of-the-art methods, demonstrating that less discriminative representations yield better cross-domain few-shot object detection performance than more abundant ones.

Zitieren

APA

Huang, Y., Mei, J., Wu, Z., Yang, Y., Zhao, H., Jiu, M., & Sahbi, H. (2026). Less Is Better: Sparse Instance Learning for Cross-Domain Few-Shot Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5176-5184. https://doi.org/10.1609/aaai.v40i7.37432

Vancouver

Huang Y, Mei J, Wu Z, Yang Y, Zhao H, Jiu M, et al. Less Is Better: Sparse Instance Learning for Cross-Domain Few-Shot Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5176-5184. doi:10.1609/aaai.v40i7.37432

BibTeX
@article{Huang2026,
  author = {Huang, Yali and Mei, Jie and Wu, Ziyi and Yang, Yiming and Zhao, Hongru and Jiu, Mingyuan and Sahbi, Hichem},
  title = {Less Is Better: Sparse Instance Learning for Cross-Domain Few-Shot Object Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5176--5184},
  doi = {10.1609/aaai.v40i7.37432}
}
Kostenlos starten →