Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection
This addresses the need for energy-efficient AI in applications like self-driving cars, though it is incremental in combining existing techniques.
The paper tackled object detection on event data by proposing Spiking CenterNet, which significantly outperformed previous work on the GEN1 Automotive Detection Dataset while using less than half the energy.
In the era of AI at the edge, self-driving cars, and climate change, the need for energy-efficient, small, embedded AI is growing. Spiking Neural Networks (SNNs) are a promising approach to address this challenge, with their event-driven information flow and sparse activations. We propose Spiking CenterNet for object detection on event data. It combines an SNN CenterNet adaptation with an efficient M2U-Net-based decoder. Our model significantly outperforms comparable previous work on Prophesee's challenging GEN1 Automotive Detection Dataset while using less than half the energy. Distilling the knowledge of a non-spiking teacher into our SNN further increases performance. To the best of our knowledge, our work is the first approach that takes advantage of knowledge distillation in the field of spiking object detection.