SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking
This work addresses energy-efficient object tracking for embedded applications, representing an incremental advance by extending SNNs to a more complex vision task.
The paper tackled object tracking by developing SiamSNN, a Siamese spiking neural network, achieving competitive performance on benchmarks like OTB2013/2015 and VOT2016/2018 with notably low energy consumption and real-time operation on a neuromorphic chip.
Recently spiking neural networks (SNNs), the third-generation of neural networks has shown remarkable capabilities of energy-efficient computing, which is a promising alternative for deep neural networks (DNNs) with high energy consumption. SNNs have reached competitive results compared to DNNs in relatively simple tasks and small datasets such as image classification and MNIST/CIFAR, while few studies on more challenging vision tasks on complex datasets. In this paper, we focus on extending deep SNNs to object tracking, a more advanced vision task with embedded applications and energy-saving requirements, and present a spike-based Siamese network called SiamSNN. Specifically, we propose an optimized hybrid similarity estimation method to exploit temporal information in the SNNs, and introduce a novel two-status coding scheme to optimize the temporal distribution of output spike trains for further improvements. SiamSNN is the first deep SNN tracker that achieves short latency and low precision loss on the visual object tracking benchmarks OTB2013/2015, VOT2016/2018, and GOT-10k. Moreover, SiamSNN achieves notably low energy consumption and real-time on Neuromorphic chip TrueNorth.