Despite the blooming success of architecture search for vision tasks in
resource-constrained environments, the design of on-device object detection
architectures have mostly been manual. The few automated search efforts are
either centered around non-mobile-friendly search spaces or not guided by
on-device latency. We propose MnasFPN, a mobile-friendly search space for the
detection head, and combine it with latency-aware architecture search to
produce efficient object detection models. The learned MnasFPN head, when
paired with MobileNetV2 body, outperforms MobileNetV3+SSDLite by 1.8 mAP at
similar latency on Pixel. It is also both 1.0 mAP more accurate and 10% faster
than NAS-FPNLite. Ablation studies show that the majority of the performance
gain comes from innovations in the search space. Further explorations reveal an
interesting coupling between the search space design and the search algorithm,
and that the complexity of MnasFPN search space may be at a local optimum.

本研究提出 MnasFPN 架构搜索空间以及结合基于延迟感知的搜索方法的对象检测模型设计，与 MobileNetV2 体系结构相匹配，优于 MobileNetV3+SSDLite 1.8 mAP，在与 NAS-FPNLite 相比，精度更高 1.0 mAP，速度更快 10%。