MnasFPN：移动设备上目标检测的学习延迟感知金字塔结构

MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices

https://arxiv.org/abs/1912.01106

日期：Dec 2019

作者：Bo Chen, Golnaz Ghiasi, Hanxiao Liu, Tsung-Yi Lin, Dmitry Kalenichenko, Hartwig Adams, Quoc V. Le

单位：Google Research

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.

尽管在资源受限的环境中，视觉任务的架构搜索取得了巨大成功，但设备上对象检测架构的设计大多是手工的。少数自动搜索工作要么集中在非移动友好搜索空间，要么不受设备延迟的影响。我们提出了MnasFPN，一个移动友好的检测头搜索空间，并将其与延迟感知架构搜索相结合，以产生高效的对象检测模型。学习的MnasFPN头与MobileNetV2体配对时，在像素上的类似延迟下比MobileNet v3+SSDLite高1.8 mAP。它也比NAS FPNLite更精确，速度快10%。消融研究表明，大部分性能增益来自搜索空间的创新。进一步的探索揭示了搜索空间设计和搜索算法之间的有趣耦合，MnasFPN搜索空间的复杂性可能处于局部最优。