Efficient IoT Inference via Context-Awareness
This addresses efficiency challenges for IoT applications by enabling scalable and context-aware inference, though it appears incremental as it builds on existing classification methods with context-aware adaptations.
The paper tackles the problem of executing deep learning-based classification on low-power IoT platforms by narrowing tasks to the current deployment context, resulting in significant improvements in accuracy, latency, and compute budget across various datasets and platforms.
While existing strategies to execute deep learning-based classification on low-power platforms assume the models are trained on all classes of interest, this paper posits that adopting context-awareness i.e. narrowing down a classification task to the current deployment context consisting of only recent inference queries can substantially enhance performance in resource-constrained environments. We propose a new paradigm, CACTUS, for scalable and efficient context-aware classification where a micro-classifier recognizes a small set of classes relevant to the current context and, when context change happens (e.g., a new class comes into the scene), rapidly switches to another suitable micro-classifier. CACTUS features several innovations, including optimizing the training cost of context-aware classifiers, enabling on-the-fly context-aware switching between classifiers, and balancing context switching costs and performance gains via simple yet effective switching policies. We show that CACTUS achieves significant benefits in accuracy, latency, and compute budget across a range of datasets and IoT platforms.