Conversion of Siamese networks to spiking neural networks for energy-efficient object tracking

Luo, Yihao; Shen, Haibo; Cao, Xiang; Wang, Tianjiang; Feng, Qianjin; Tan, Zehan

doi:10.1007/s00521-022-06984-1

Cited by 15 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering that the Siamese networks have achieved remarkable performances in object tracking, SiamSNN was constructed by conversion to achieve short latency and low precision degradation on several benchmarks (Luo et al, 2022). Similarly, the directly trained Spiking SiamFC++ showed a small precision loss compared to the original SiamFC++ (Xiang et al, 2022).…”

Section: Object Detection and Object Trackingmentioning

confidence: 99%

Legally demystifying an oriental cultural myth: reinterpreting Guanxi in reference to contract law

Zhou¹

2021

Peking University Law Journal

View full text Add to dashboard Cite

Spiking Transformers, which integrate Spiking Neural Networks (SNNs) with Transformer architectures, have attracted significant attention due to their potential for energy efficiency and high performance. However, existing models in this domain still suffer from suboptimal performance. We introduce several innovations to improve the performance: i) We propose a novel spike-form Q-K attention mechanism, tailored for SNNs, which efficiently models the importance of token or channel dimensions through binary vectors with linear complexity. ii) We incorporate the hierarchical structure, which significantly benefits the performance of both the brain and artificial neural networks, into spiking transformers to obtain multi-scale spiking representation. iii) We design a versatile and powerful patch embedding module with a deformed shortcut specifically for spiking transformers. Together, we develop QKFormer, a hierarchical spiking transformer based on Q-K attention with direct training. QKFormer shows significantly superior performance over existing state-of-the-art SNN models on various mainstream datasets. Notably, with comparable size to Spikformer (66.34 M, 74.81%), QKFormer (64.96 M) achieves a groundbreaking top-1 accuracy of 85.65% on ImageNet-1k, substantially outperforming Spikformer by 10.84%. To our best knowledge, this is the first time that directly training SNNs have exceeded 85% accuracy on ImageNet-1K. The code and models are publicly available at https://github.com/ zhouchenlin2096/QKFormer.

show abstract

Section: Object Detection and Object Trackingmentioning

confidence: 99%

Legally demystifying an oriental cultural myth: reinterpreting Guanxi in reference to contract law

Zhou¹

2021

Peking University Law Journal

View full text Add to dashboard Cite

show abstract

“…By using techniques such as channelby-channel normalization and signed neurons with imbalanced thresholds, it provided a faster and more accurate message transmission between neurons, achieving better convergence performance and lower energy consumption than the ANN model. Luo et al [27] first proposed the target tracker SiamSNN based on SNNs, which has good accuracy and can achieve real-time tracking on the neural morphology chip TrueNorth [28]. Fang et al [29] proposed a residual network based on the spiking neurons to solve the image classification problems by adding the SNN neural layers between the traditional residual units.…”

Section: Introductionmentioning

confidence: 99%

Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images

Jiang,

Xie,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Ship classification using the synthetic aperture radar (SAR) images has a significant role in remote sensing applications. Aiming at the problems of excessive model parameters numbers and high energy consumption in the traditional deep learning methods for the SAR ship classification, this paper provides an energy-efficient SAR ship classification paradigm that combines spiking neural networks (SNNs) with Siamese network architecture, for the first time in the field of SAR ship classification, which is called the Siam-SpikingShipCLSNet. It combines the advantage of SNNs in energy consumption and the advantage of the idea in performances that use the Siamese neuron network to fuse the features from dual-polarized SAR images. Additionally, we migrated the feature fusion strategy from CNN-based Siamese neural networks to the SNN domain and analyzed the effects of various spiking feature fusion methods on the Siamese SNN. Finally, an end-to-end error backpropagation optimization method based on the surrogate gradient has been adopted to train this model. Experimental results tested on the OpenSARShip2.0 dataset have demonstrated the correctness and effectiveness of the proposed SAR ship classification strategy, which has the advantages of the higher accuracy, fewer parameters and lower energy consumption compared with the mainstream deep learning method of the SAR ship classification.

show abstract

RETRACTED ARTICLE: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

Ramesh,

Revoori,

Edla

et al. 2023

Soft Comput

View full text Add to dashboard Cite

Conversion of Siamese networks to spiking neural networks for energy-efficient object tracking

Cited by 15 publications

References 53 publications

Legally demystifying an oriental cultural myth: reinterpreting Guanxi in reference to contract law

Legally demystifying an oriental cultural myth: reinterpreting Guanxi in reference to contract law

Energy-Efficient and High-Performance Ship Classification Strategy Based on Siamese Spiking Neural Network in Dual-Polarized SAR Images

RETRACTED ARTICLE: A novel multi-layer multi-spiking neural network for EEG signal classification using Mini Batch SGD

Contact Info

Product

Resources

About