Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909217935327232 |
|---|---|
| author | Bodden, Lennard Schwaiger, Franziska Ha, Duc Bach Kreuzberg, Lars Behnke, Sven |
| author_facet | Bodden, Lennard Schwaiger, Franziska Ha, Duc Bach Kreuzberg, Lars Behnke, Sven |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01287 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection Bodden, Lennard Schwaiger, Franziska Ha, Duc Bach Kreuzberg, Lars Behnke, Sven Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing 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. |
| title | Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2402.01287 |