IdeNet: Making Neural Network Identify Camouflaged Objects Like Creatures
IEEE Transactions on Image Processing · 2024 · 33 · 4824-4839
DOI: 10.1109/tip.2024.3449574 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Juwei Guan und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Neural Networks, Computer, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Jiangsu Provincial Key Research and Development Program, China Computer Federation (CCF)-Huawei Populus Grove Fund, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Camouflaged objects often blend in with their surroundings, making the perception of a camouflaged object a more complex procedure. However, most neural-network-based methods that simulate the visual information processing pathway of creatures only roughly define the general process, which deficiently reproduces the process of identifying camouflaged objects. How to make modeled neural networks perceive camouflaged objects as effectively as creatures is a significant topic that deserves further consideration. After meticulous analysis of biological visual information processing, we propose an end-to-end prudent and comprehensive neural network, termed IdeNet, to model the critical information processing. Specifically, IdeNet divides the entire perception process into five stages: information collection, information augmentation, information filtering, information localization, and information correction and object identification. In addition, we design tailored visual information processing mechanisms for each stage, including the information augmentation module (IAM), the information filtering module (IFM), the information localization module (ILM), and the information correction module (ICM), to model the critical visual information processing and establish the inextricable association of biological behavior and visual information processing. The extensive experiments show that IdeNet outperforms state-of-the-art methods in all benchmarks, demonstrating the effectiveness of the five-stage partitioning of visual information processing pathway and the tailored visual information processing mechanisms for camouflaged object detection. Our code is publicly available at: https://github.com/whyandbecause/IdeNet.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- Jiangsu Provincial Key Research and Development Program
- China Computer Federation (CCF)-Huawei Populus Grove Fund, Fundamental Research Funds for the Central Universities
- Jiangsu Provincial Key Laboratory of Network and Information Security
- Collaborative Innovation Center of Novel Software Technology and Industrialization
Zitieren
APA
Guan, J., Fang, X., Zhu, T., Cai, Z., Ling, Z., Yang, M., & Luo, J. (2024). IdeNet: Making Neural Network Identify Camouflaged Objects Like Creatures. IEEE Transactions on Image Processing, 33, 4824-4839. https://doi.org/10.1109/tip.2024.3449574
Vancouver
Guan J, Fang X, Zhu T, Cai Z, Ling Z, Yang M, et al. IdeNet: Making Neural Network Identify Camouflaged Objects Like Creatures. IEEE Transactions on Image Processing. 2024;33:4824-4839. doi:10.1109/tip.2024.3449574
BibTeX
@article{Guan2024,
author = {Guan, Juwei and Fang, Xiaolin and Zhu, Tongxin and Cai, Zhipeng and Ling, Zhen and Yang, Ming and Luo, Junzhou},
title = {IdeNet: Making Neural Network Identify Camouflaged Objects Like Creatures},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {4824--4839},
doi = {10.1109/tip.2024.3449574}
}
EUVIMED