让微型无人机提前跳过无目标帧，提升检测效率
BlankSkip: Early-exit Object Detection onboard Nano-drones
- 用辅助分类任务判断画面是否含目标，无则提前退出
- 实测平均吞吐提升24%，精度仅降0.015 mAP
- 适合资源受限的微型无人机实时目标检测
在微型无人机上部署小型计算机视觉深度神经网络是实现自主飞行的关键，但受限于极低的计算资源（约10 MiB内存，1 W功耗）。早期退出自适应网络通过降低“易处理”输入帧的计算量，可有效减少平均推理延迟。然而，该方法在分类任务中已广泛研究，应用于密集型任务如目标检测（OD）时面临挑战。本文提出BlankSkip，一种基于简单辅助分类任务的自适应目标检测网络，通过识别无兴趣目标的帧实现早期退出。在真实微型无人机平台Bitcraze Crazyflie 2.1上的实验表明，相比静态MobileNet-SSD检测器，在最新纳米无人机目标检测数据集上，平均吞吐提升达24%，仅带来0.015 mAP的精度下降。
原文摘要 · Abstract (English)
Deploying tiny computer vision Deep Neural Networks (DNNs) on-board nano-sized drones is key for achieving autonomy, but is complicated by the extremely tight constraints of their computational platforms (approximately 10 MiB memory, 1 W power budget). Early-exit adaptive DNNs that dial down the computational effort for "easy-to-process" input frames represent a promising way to reduce the average inference latency. However, while this approach is extensively studied for classification, its application to dense tasks like object detection (OD) is not straightforward. In this paper, we propose BlankSkip, an adaptive network for on-device OD that leverages a simple auxiliary classification task for early exit, i.e., identifying frames with no objects of interest. With experiments using a real-world nano-drone platform, the Bitcraze Crazyflie 2.1, we achieve up to 24% average throughput improvement with a limited 0.015 mean Average Precision (mAP) drop compared to a static MobileNet-SSD detector, on a state-of-the-art nano-drones OD dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。