BLADE: Reliable Dynamic Hardware-Aware SNN-ANN Boundary Selection for Event-Based Object Detection
This paper proposes a hardware-aware method for selecting the boundary between spiking and artificial neural networks to improve event-based object detection, a technical efficiency advance with no direct safety implications.
This paper proposes a hardware-aware method for selecting the boundary between spiking and artificial neural networks to improve event-based object detection, a technical efficiency advance with no direct safety implications.
Auto-scored: A narrow technical efficiency improvement in event-based vision with no identified risk or mitigation relevance.