In object detection, the detection backbone consumes more than half of the overall inference cost. Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS). However, existing NAS methods for object detection require hundreds to thousands of GPU hours of searching, making them impractical in fast-paced research and development. In this work, we propose a novel zero-shot NAS method to address this issue. The proposed method, named MAE-DET, automatically designs efficient detection backbones via the Maximum Entropy Principle without training network parameters, reducing the architecture design cost to nearly zero yet delivering the state-of-the-art (SOTA) performance. Under the hood, MAE-DET maximizes the differential entropy of detection backbones, leading to a better feature extractor for object detection under the same computational budgets. After merely one GPU day of fully automatic design, MAE-DET innovates SOTA detection backbones on multiple detection benchmark datasets with little human intervention. Comparing to ResNet-50 backbone, MAE-DET is $+2.0\%$ better in mAP when using the same amount of FLOPs/parameters, and is $1.54$ times faster on NVIDIA V100 at the same mAP.
翻译:在目标探测中,探测主干网耗资一半以上的总推算成本。最近的研究试图通过在神经结构搜索(NAS)的帮助下优化主干结构来降低这一成本。然而,现有的天体探测方法需要数百至数千个GPU小时的搜索,使其在快速的研究和开发中不切实际。在这项工作中,我们提出了一个新的零射NAS方法来解决这个问题。拟议的方法名为MAE-DET,在没有培训网络参数的情况下,通过最大导体原则自动设计高效的探测主干网,将建筑设计费用降低到近零,但交付了最先进的(SOTA)性能。在引擎下,MAE-DET最大限度地增加探测主干网的微分数,导致在同一计算预算下更好地进行天全自动设计后,MAE-DET创新SOTA在多个探测基准数据集上探测主干线上进行自动探测。与ResNet-50主干线相比,MAE-DET是美元+1美元/美元,在更快的MAPA中,在使用同一数额时,MA1美元/美元为1.5美元/美元。