AI RESEARCH

ELASTIC: Efficient Once For All Iterative Search for Object Detection on Microcontrollers

arXiv CS.LG

ArXi:2503.21999v3 Announce Type: replace-cross Deploying high-performance object detectors on TinyML platforms poses significant challenges due to tight hardware constraints and the modular complexity of modern detection pipelines. Neural Architecture Search (NAS) offers a path toward automation, but existing methods either restrict optimization to individual modules, sacrificing cross-module synergy, or require global searches that are computationally intractable.