VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual System

In the rapidly advancing realms of computer vision and artificial intelligence, the quest for human-like intelligence is escalating. Central to this pursuit is visual perception, with the human eye as a paragon of efficiency in the natural world. Recent research has prominently embraced the emulatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaofei Li, Yufan Mao, Mingshan Zhong, Jun Zhao
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Applied Artificial Intelligence
Online Access:https://www.tandfonline.com/doi/10.1080/08839514.2024.2335100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850255162624442368
author Zhaofei Li
Yufan Mao
Mingshan Zhong
Jun Zhao
author_facet Zhaofei Li
Yufan Mao
Mingshan Zhong
Jun Zhao
author_sort Zhaofei Li
collection DOAJ
description In the rapidly advancing realms of computer vision and artificial intelligence, the quest for human-like intelligence is escalating. Central to this pursuit is visual perception, with the human eye as a paragon of efficiency in the natural world. Recent research has prominently embraced the emulation of the human eye’s visual system in computer vision. This paper introduces a pioneering approach, the visually-aware biomimetic network (VBNet), composed of a dual-branch parallel architecture: a Transformer branch emulating the peripheral retina for global feature dependencies and a CNN branch resembling the macular region for local details. Furthermore, it employs feature converter modules (CFC and TFC) to enhance information fusion between the branches. Empirical results highlight VBNet’s superiority over RegNet and PVT in ImageNet classification and competitive performance in MSCOCO object detection and instance segmentation. The dual-branch design, akin to the human visual system, enables simultaneous focus on local and global features, offering fresh perspectives for future research in the field of computer vision and artificial intelligence.
format Article
id doaj-art-42bb22a7422d49f2a1934c6964f3e34b
institution OA Journals
issn 0883-9514
1087-6545
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Applied Artificial Intelligence
spelling doaj-art-42bb22a7422d49f2a1934c6964f3e34b2025-08-20T01:56:56ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452024-12-0138110.1080/08839514.2024.2335100VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual SystemZhaofei Li0Yufan Mao1Mingshan Zhong2Jun Zhao3College of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, ChinaCollege of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, ChinaCollege of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, ChinaCollege of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin, ChinaIn the rapidly advancing realms of computer vision and artificial intelligence, the quest for human-like intelligence is escalating. Central to this pursuit is visual perception, with the human eye as a paragon of efficiency in the natural world. Recent research has prominently embraced the emulation of the human eye’s visual system in computer vision. This paper introduces a pioneering approach, the visually-aware biomimetic network (VBNet), composed of a dual-branch parallel architecture: a Transformer branch emulating the peripheral retina for global feature dependencies and a CNN branch resembling the macular region for local details. Furthermore, it employs feature converter modules (CFC and TFC) to enhance information fusion between the branches. Empirical results highlight VBNet’s superiority over RegNet and PVT in ImageNet classification and competitive performance in MSCOCO object detection and instance segmentation. The dual-branch design, akin to the human visual system, enables simultaneous focus on local and global features, offering fresh perspectives for future research in the field of computer vision and artificial intelligence.https://www.tandfonline.com/doi/10.1080/08839514.2024.2335100
spellingShingle Zhaofei Li
Yufan Mao
Mingshan Zhong
Jun Zhao
VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual System
Applied Artificial Intelligence
title VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual System
title_full VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual System
title_fullStr VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual System
title_full_unstemmed VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual System
title_short VBNet: A Visually-Aware Biomimetic Network for Simulating the Human Eye’s Visual System
title_sort vbnet a visually aware biomimetic network for simulating the human eye s visual system
url https://www.tandfonline.com/doi/10.1080/08839514.2024.2335100
work_keys_str_mv AT zhaofeili vbnetavisuallyawarebiomimeticnetworkforsimulatingthehumaneyesvisualsystem
AT yufanmao vbnetavisuallyawarebiomimeticnetworkforsimulatingthehumaneyesvisualsystem
AT mingshanzhong vbnetavisuallyawarebiomimeticnetworkforsimulatingthehumaneyesvisualsystem
AT junzhao vbnetavisuallyawarebiomimeticnetworkforsimulatingthehumaneyesvisualsystem