Spiking SiamFC++: Deep Spiking Neural Network for Object Tracking. (arXiv:2209.12010v1 [cs.CV])

Spiking neural network (SNN) is a biologically-plausible model and exhibits
advantages of high computational capability and low power consumption. While
the training of deep SNN is still an open problem, which limits the real-world
applications of deep SNN. Here we propose a deep SNN architecture named Spiking
SiamFC++ for object tracking with end-to-end direct training. Specifically, the
AlexNet network is extended in the time domain to extract the feature, and the
surrogate gradient function is adopted to realize direct supervised …

arxiv network neural network spiking neural network tracking