Efficient detectors for edge devices are often optimized for metrics like parameters or speed counts, which remain weak correlation with the energy of detectors. However, among vision applications of convolutional neural networks (CNNs), some, such as always-on surveillance cameras, are critical for energy constraints. This paper aims to serve as a baseline by designing detectors to reach tradeoffs between energy and performance from two perspectives: 1) We extensively analyze various CNNs to identify low-energy architectures, including the selection of activation functions, convolutions operators, and feature fusion structures on necks. These underappreciated details in past works seriously affect the energy consumption of detectors; 2) To break through the dilemmatic energy-performance problem, we propose a balanced detector driven by energy using discovered low-energy components named \textit{FemtoDet}. In addition to the novel construction, we further improve FemtoDet by considering convolutions and training strategy optimizations. Specifically, we develop a new instance boundary enhancement (IBE) module for convolution optimization to overcome the contradiction between the limited capacity of CNNs and detection tasks in diverse spatial representations, and propose a recursive warm-restart (RecWR) for optimizing training strategy to escape the sub-optimization of light-weight detectors, considering the data shift produced in popular augmentations. As a result, FemtoDet with only 68.77k parameters achieves a competitive score of 46.3 AP50 on PASCAL VOC and power of 7.83W on RTX 3090. Extensive experiments on COCO and TJU-DHD datasets indicate that the proposed method achieves competitive results in diverse scenes.
翻译:边缘装置的高效探测器往往被优化,用于测量参数或速度计数等测量度,这些参数或速度计数与探测器的能量关系仍然薄弱。然而,在革命性神经网络(CNNs)的视觉应用中,有些(例如总是在监视摄像机上)对能源限制至关重要。本文件的目的是设计探测器,从两个角度来权衡能源与性能之间的取舍,以此作为基线。 1)我们广泛分析各种CNN,以确定低能源结构,包括选择激活功能、电动操作员和颈部的集成结构。这些过去作品中未得到充分理解的细节严重影响了探测器的能源消耗;2 要打破两难的能源性能表现问题,我们建议使用所发现的低能量部件驱动的平衡探测器,名为\ textitit{FemtoDet}。 除了新构思之外,我们还通过考虑电动和培训战略优化,进一步改进FemtoDett。我们开发一个新的图像增强级阵列(IBEBE)模块,以便克服CNIS能力有限的能力和探测任务之间在不同的空间剖面展示中的检测任务之间矛盾;2-803,我们建议利用已生成的S-regy-regreal-real-real-real-regildal结果,以实现30-regregal-real-real-regal-regal-real-regal-regal-res制成的30-regal-regal-real-real-real-real-real-real-real-regal-regal-regal-regal-regal-regal-regal-real-real-real-real-real-real-real-real-real-real-real-real-real-real-real-real-real-real-