EUVIMEDEUVIMED entdecken
Crossref

Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment

Zeyu Shangguan, Daniel Seita, Mohammad Rostami

International Journal of Computer Vision · 2026-06 · 134 (6)

DOI: 10.1007/s11263-026-02839-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 07.05.2026. Verfasst von Zeyu Shangguan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 82 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advancements in cross-modal feature extraction and integration have significantly enhanced performance in few-shot learning tasks. However, current multi-modal object detection (MM-OD) methods often experience notable performance degradation when encountering substantial domain shifts. We propose that incorporating rich textual information can enable the model to establish a more robust knowledge relationship between visual instances and their corresponding language descriptions, thereby mitigating the challenges of domain shift. Specifically, we focus on the problem of Cross-Domain Multi-Modal Few-Shot Object Detection (CDMM-FSOD) and introduce a meta-learning-based framework designed to leverage rich textual semantics as an auxiliary modality to achieve effective domain adaptation. Our new architecture incorporates two key components: (i) A multi-modal feature aggregation module, which aligns visual and linguistic feature embeddings to ensure cohesive integration across modalities. (ii) A rich text semantic rectification module, which employs bidirectional text feature generation to refine multi-modal feature alignment, thereby enhancing understanding of language and its application in object detection. We evaluate the proposed method on three cross-domain object detection benchmarks and demonstrate that it significantly surpasses existing few-shot object detection approaches. The implementation of our method is publicly accessible at: https://github.com/zshanggu/CDMM..

Zitieren

APA

Shangguan, Z., Seita, D., & Rostami, M. (2026). Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment. International Journal of Computer Vision, 134(6). https://doi.org/10.1007/s11263-026-02839-7

Vancouver

Shangguan Z, Seita D, Rostami M. Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment. International Journal of Computer Vision. 2026;134(6). doi:10.1007/s11263-026-02839-7

BibTeX
@article{Shangguan2026,
  author = {Shangguan, Zeyu and Seita, Daniel and Rostami, Mohammad},
  title = {Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment},
  journal = {International Journal of Computer Vision},
  year = {2026},
  volume = {134},
  number = {6},
  doi = {10.1007/s11263-026-02839-7}
}
Kostenlos starten →