EUVIMEDEUVIMED entdecken
Crossref

Paint outside the box: synthesizing and selecting training data for visual grounding

Zilin Du, Haoxin Li, Jianfei Yu, Boyang Li

Machine Vision and Applications · 2026-11 · 37 (6)

DOI: 10.1007/s00138-026-01928-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Vision and Applications, online erschienen am 10.10.2026. Verfasst von Zilin Du und 3 weiteren Autor:innen. Die Arbeit nennt 123 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Visual grounding aims to localize the image regions based on a textual query. Given the difficulty of large-scale data curation, we investigate how to effectively learn visual grounding under data-scarce settings in this paper. To address the data scarcity, we propose a novel framework, POBF (Paint Outside the Box and Filter). POBF synthesizes images by inpainting outside the box, tackling a label misalignment issue encountered in previous works. Furthermore, POBF leverages an innovative filtering scheme to select the most effective training data. This scheme combines a hardness score and an overfitting score, balanced by a penalty term. Extensive experiments across four benchmark datasets demonstrate that POBF consistently improves performance, achieving an average gain of 5.83% over the real-data-only method and outperforming leading baselines by 2.29–3.85% in accuracy. We validate the robustness and generalizability of POBF across various generative models, training data sizes, and model architectures.

Zitieren

APA

Du, Z., Li, H., Yu, J., & Li, B. (2026). Paint outside the box: synthesizing and selecting training data for visual grounding. Machine Vision and Applications, 37(6). https://doi.org/10.1007/s00138-026-01928-4

Vancouver

Du Z, Li H, Yu J, Li B. Paint outside the box: synthesizing and selecting training data for visual grounding. Machine Vision and Applications. 2026;37(6). doi:10.1007/s00138-026-01928-4

BibTeX
@article{Du2026,
  author = {Du, Zilin and Li, Haoxin and Yu, Jianfei and Li, Boyang},
  title = {Paint outside the box: synthesizing and selecting training data for visual grounding},
  journal = {Machine Vision and Applications},
  year = {2026},
  volume = {37},
  number = {6},
  doi = {10.1007/s00138-026-01928-4}
}
Kostenlos starten →