EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition

Chaofei Qi iD, Peng Li, Weiyang Lin iD

Biomimetics · 18.07.2026 · 11 (7) · 505

DOI: 10.3390/biomimetics11070505 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 18.07.2026. Verfasst von Chaofei Qi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Science & Technology Project of Anhui Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humans possess unique advantages in dealing with few-shot visual recognition scenarios, inspiring the development of meta-learning methods aimed at emulating these abilities. Current mainstream meta-learning primarily utilizes the monocular vision or the dual asymmetric complementary architectures, collectively referred to as Machine-visual Meta-Learning (MvML). Nevertheless, research has not yet developed an architecture for simulating the human binocular visual system, named Humanoid-visual Meta-Learning (HvML). This paper innovatively proposes an excellent paradigm BPIAL belonging to the HvML: Binocular Perception Instance Authentication Learning, which can alleviate the monocular shallowness and dual-branch processing instability of MvML. Structurally, our BPIAL comprises two interconnected binocular perception and information processing modules: BSEM and IAPM. The former module can simulate binocular visual field extraction, feature extraction and compression, and channel dimension reduction, while IAPM can simulate the logic, reasoning, and judgment processes of the two human visual branches and the brain. We have demonstrated the feasibility and correctness of BPIAL on five benchmarks. Sufficient and comparative experiments with the state-of-the-art methods have proved its superiority and effectiveness.

Schlagwörter

Stichwörter der Autor:innen

Machine visual Meta-Learningbinocular sensingfew-shot learninghumanoid visual meta-learninginstance authentication

Autor:innen und Institutionen

  • Faculty of Computing, Harbin Institute of Technology, Harbin 150001, China.
  • School of Mechanical Engineering and Automation, Harbin Institute of Technology Shenzhen, Shenzhen 518055, China.
  • Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin 150001, China.

ORCID-Profile: Chaofei Qi, Weiyang Lin

Förderung

  • National Natural Science Foundation of China
  • Key Science & Technology Project of Anhui Province

Zitieren

APA

Qi, C., Li, P., & Lin, W. (2026). Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition. Biomimetics, 11(7), 505. https://doi.org/10.3390/biomimetics11070505

Vancouver

Qi C, Li P, Lin W. Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition. Biomimetics. 2026;11(7):505. doi:10.3390/biomimetics11070505

BibTeX
@article{Qi2026,
  author = {Qi, Chaofei and Li, Peng and Lin, Weiyang},
  title = {Binocular Perception Instance Authentication Learning for Few-Shot Visual Recognition},
  journal = {Biomimetics},
  year = {2026},
  volume = {11},
  number = {7},
  pages = {505},
  doi = {10.3390/biomimetics11070505}
}
Kostenlos starten →