Spiking Neural Networks for Object Detection Based on Integrating Neuronal Variants and Self-Attention Mechanisms

被引：1

作者：

Li, Weixuan ^{[1
]}

Zhao, Jinxiu ^{[1
]}

Su, Li ^{[1
]}

Jiang, Na ^{[1
]}

Hu, Quan ^{[2
]}

机构：

[1] Capital Normal Univ, Sch Informat Engn, Beijing 100048, Peoples R China

[2] Beijing Inst Technol, Sch Aerosp Engn, Beijing 100081, Peoples R China

来源：

APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 20期

基金：

北京市自然科学基金; 中国国家自然科学基金;

关键词：

object detection; spiking neural networks; neuronal variants; attention mechanism; MODEL;

D O I：

10.3390/app14209607

中图分类号：

O6 [化学];

学科分类号：

0703 ;

摘要：

Thanks to their event-driven asynchronous computing capabilities and low power consumption advantages, spiking neural networks (SNNs) show significant potential for computer vision tasks, especially in object detection. However, effective training methods and optimization mechanisms for SNNs remain underexplored. This study proposes two high accuracy SNNs for object detection, AMS_YOLO and AMSpiking_VGG, integrating neuronal variants and attention mechanisms. To enhance these proposed networks, we explore the impact of incorporating different neuronal variants.The results show that the optimization in the SNN's structure with neuronal variants outperforms that in the attention mechanism for object detection. Compared to the state-of-the-art in the current SNNs, AMS_YOLO improved by 6.7% in accuracy on the static dataset COCO2017, and AMS_Spiking has improved by 11.4% on the dynamic dataset GEN1.

引用

页数：13

共 50 条

[11] Progressive Domain Adaptive Object Detection Based on Self-Attention in Foggy Weather [J].

Lin, Meng ;

Zhou, Gang ;

Yang, Yawei ;

Shi, Jun .

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2023, 18 (12) :1923-1931

[12] Embedded event based object detection with spiking neural network [J].

Courtois, Jonathan ;

Novac, Pierre-Emmanuel ;

Lemaire, Edgar ;

Pegatoquet, Alain ;

Miramond, Benoit .

2024 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN 2024, 2024,

[13] Object Detection Model Based on Scene-Level Region Proposal Self-Attention [J].

Quan, Yu ;

Li, Zhixin ;

Zhang, Canlong ;

Ma, Huifang .

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, :954-961

[14] DPNET: DUAL-PATH NETWORK FOR EFFICIENT OBJECT DETECTION WITH LIGHTWEIGHT SELF-ATTENTION [J].

Shi, Huimin ;

Zhou, Quan ;

Ni, Yinghao ;

Wu, Xiaofu ;

Latecki, Longin Jan .

2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2022, :771-775

[15] SpotNet: Self-Attention Multi-Task Network for Object Detection [J].

Perreault, Hughes ;

Bilodeau, Guillaume-Alexandre ;

Saunier, Nicolas ;

Heritier, Maguelonne .

2020 17TH CONFERENCE ON COMPUTER AND ROBOT VISION (CRV 2020), 2020, :230-237

[16] Tiny Object Detection via Regional Cross Self-Attention Network [J].

Cheng, Keyang ;

Cui, Honggang ;

Ghafoor, Humaira Abdul ;

Wan, Hao ;

Mao, Qirong ;

Zhan, Yongzhao .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (10) :8984-8996

[17] Integrating object proposal with attention networks for video saliency detection [J].

Jian, Muwei ;

Wang, Jiaojin ;

Yu, Hui ;

Wang, Gai-Ge .

INFORMATION SCIENCES, 2021, 576 :819-830

[18] Self-Attention Guidance and Multiscale Feature Fusion-Based UAV Image Object Detection [J].

Zhang, Yunzuo ;

Wu, Cunyu ;

Zhang, Tian ;

Liu, Yameng ;

Zheng, Yuxin .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20

[19] Direct training high-performance spiking neural networks for object recognition and detection [J].

Zhang, Hong ;

Li, Yang ;

He, Bin ;

Fan, Xiongfei ;

Wang, Yue ;

Zhang, Yu .

FRONTIERS IN NEUROSCIENCE, 2023, 17

[20] Deep Directly-Trained Spiking Neural Networks for Object Detection [J].

Su, Qiaoyi ;

Chou, Yuhong ;

Hu, Yifan ;

Li, Jianing ;

Mei, Shijie ;

Zhang, Ziyang ;

Li, Guoqi .

2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, :6532-6542

← 1 2 3 4 5 →