Spiking Neural Networks for Frame-based and Event-based Single Object Localization
This work addresses energy-efficient object localization for neuromorphic vision applications, but it is incremental as it builds on existing spiking network methods with a focus on sensor-specific adaptations.
The paper tackles the problem of single object localization using spiking neural networks for frame- and event-based sensors, showing competitive or better performance in accuracy, robustness against corruptions, and lower energy consumption compared to artificial neural networks.
Spiking neural networks have shown much promise as an energy-efficient alternative to artificial neural networks. However, understanding the impacts of sensor noises and input encodings on the network activity and performance remains difficult with common neuromorphic vision baselines like classification. Therefore, we propose a spiking neural network approach for single object localization trained using surrogate gradient descent, for frame- and event-based sensors. We compare our method with similar artificial neural networks and show that our model has competitive/better performance in accuracy, robustness against various corruptions, and has lower energy consumption. Moreover, we study the impact of neural coding schemes for static images in accuracy, robustness, and energy efficiency. Our observations differ importantly from previous studies on bio-plausible learning rules, which helps in the design of surrogate gradient trained architectures, and offers insight to design priorities in future neuromorphic technologies in terms of noise characteristics and data encoding methods.