Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment
This addresses the need for scalable and efficient model updates in edge camera systems, though it appears incremental as it builds on existing active learning and distillation methods.
The paper tackles the problem of selecting the most useful images for training edge models to maximize quality while minimizing transmission costs, showing that a high-confidence stream-based strategy with diversity yields a high-quality model with minimal dataset queries.
Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central server to annotate data, which is then used to train smaller models tailored to the edge devices with limited computational power. This work explores how to select the most useful images for training to maximize model quality while keeping transmission costs low. Our work shows that, for a similar training load (i.e., iterations), a high-confidence stream-based strategy coupled with a diversity-based approach produces a high-quality model with minimal dataset queries.