A fine-grained split inference system enables CNN models infeasible on single MCUs to run across networked devices by partitioning at sub-layer granularity, reducing per-device peak RAM while keeping practical latency.
A global approach for goal-driven pruning of object recognition networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Split CNN Inference on Networked Microcontrollers
A fine-grained split inference system enables CNN models infeasible on single MCUs to run across networked devices by partitioning at sub-layer granularity, reducing per-device peak RAM while keeping practical latency.