论文标题
复杂对象探测器的拆分计算：挑战和初步结果
Split Computing for Complex Object Detectors: Challenges and Preliminary Results
论文作者
论文摘要
遵循DNN模型的移动和边缘计算趋势，一种中间选项，分裂计算引起了研究社区的关注。先前的研究从经验上表明，尽管移动和边缘计算通常是总推断时间方面的最佳选择，但在某些情况下，拆分计算方法可以实现更短的推理时间。但是，所有提出的拆分计算方法都集中在图像分类任务上，并且大多数都使用远离实际情况的小数据集进行评估。在本文中，我们讨论了在大型数据集中训练的强大R-CNN对象检测器，可可2017的挑战。我们通过层次张量的大小和模型大小进行了广泛的分析对象探测器，并表明天真的拆分计算方法不会降低推荐时间。据我们所知，这是第一次将小瓶颈注入此类对象探测器并揭示分裂计算方法的潜力的研究。本研究中使用的源代码和受过训练的模型的权重可在https://github.com/yoshitomo-matsubara/hhnd-ghnd-ghnd-object-detectors上获得。
Following the trends of mobile and edge computing for DNN models, an intermediate option, split computing, has been attracting attentions from the research community. Previous studies empirically showed that while mobile and edge computing often would be the best options in terms of total inference time, there are some scenarios where split computing methods can achieve shorter inference time. All the proposed split computing approaches, however, focus on image classification tasks, and most are assessed with small datasets that are far from the practical scenarios. In this paper, we discuss the challenges in developing split computing methods for powerful R-CNN object detectors trained on a large dataset, COCO 2017. We extensively analyze the object detectors in terms of layer-wise tensor size and model size, and show that naive split computing methods would not reduce inference time. To the best of our knowledge, this is the first study to inject small bottlenecks to such object detectors and unveil the potential of a split computing approach. The source code and trained models' weights used in this study are available at https://github.com/yoshitomo-matsubara/hnd-ghnd-object-detectors .
