Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing
This work addresses efficiency problems for embedded smart devices, enabling real-time radar data processing, though it appears incremental as it builds on existing Early Exit Networks.
The paper tackles the challenge of processing streaming radar data on resource-constrained embedded devices by introducing novel techniques that leverage temporal correlation to enhance Early Exit Neural Networks, resulting in up to 26% reduction in operations per inference compared to a Single Exit Network.
Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal correlation present in streaming radar data to enhance the efficiency of Early Exit Neural Networks for Deep Learning inference on embedded devices. These networks add additional classifier branches between the architecture's hidden layers that allow for an early termination of the inference if their result is deemed sufficient enough by an at-runtime decision mechanism. Our methods enable more informed decisions on when to terminate the inference, reducing computational costs while maintaining a minimal loss of accuracy. Our results demonstrate that our techniques save up to 26% of operations per inference over a Single Exit Network and 12% over a confidence-based Early Exit version. Our proposed techniques work on commodity hardware and can be combined with traditional optimizations, making them accessible for resource-constrained embedded platforms commonly used in smart devices. Such efficiency gains enable real-time radar data processing on resource-constrained platforms, allowing for new applications in the context of smart homes, Internet-of-Things, and human-computer interaction.