<ul><li>Neural Architecture Search (NAS) for deep learning object detection frameworks is computationally expensive due to the vast search space.</li><li>The proposed method, FACETS, is a unified iterative NAS technique that refines the architecture of all modules cyclically.</li><li>FACETS reduces the search space, preserves interdependencies among modules, and incorporates constraints based on the target device's computational budget.</li><li>FACETS achieves higher accuracy and faster search compared to progressive and single-module search strategies.</li></ul>

FACETS: Efficient Once-for-all Object Detection via Constrained Iterative Search

Discover more