Accuracy-Constrained Efficiency Optimization and GPU Profiling of CNN Inference for Detecting Drainage Crossing Locations
Accuracy-Constrained Efficiency Optimization and GPU Profiling of CNN Inference for Detecting Drainage Crossing Locations
复制标题
DOI：
10.1145/3624062.3624260
复制
发表时间：
2023-11
期刊：
影响因子：
--
通讯作者：
Yicheng Zhang;Dhroov Pandey;Di Wu;Turja Kundu;Ruopu Li;Tong Shu
中科院分区：
文献类型：
--
作者：
Yicheng Zhang;Dhroov Pandey;Di Wu;Turja Kundu;Ruopu Li;Tong Shu
准确、高效地确定水文连通性已引起学术界和工业界的高度重视，因为它对环境管理具有重要意义。虽然最近的研究利用了水文特征的空间特征，但使用高程模型来确定排水路径可能会受到水流障碍的影响。为了应对这些挑战，我们在这项研究中的重点是通过应用先进的卷积神经网络(CNN)来检测排水交叉路口。为了实现这一目标，我们使用神经体系结构搜索来自动探索CNN模型以识别排水交叉路口。该方法不仅具有较高的目标检测准确率(平均准确率在97%以上)，而且在很短的时间内(0.268 ms)就能有效地推断出正确的排水通道。此外，我们在GPU系统上对我们的方法进行了详细的剖析，以分析性能瓶颈。
The accurate and efficient determination of hydrologic connectivity has garnered significant attention from both academic and industrial sectors due to its critical implications for environmental management. While recent studies have leveraged the spatial characteristics of hydrologic features, the use of elevation models for identifying drainage paths can be influenced by flow barriers. To address these challenges, our focus in this study is on detecting drainage crossings through the application of advanced convolutional neural networks (CNNs). In pursuit of this goal, we use neural architecture search to automatically explore CNN models for identifying drainage crossings. Our approach not only attains high accuracy (over 97% for average precision) in object detection but also excels in efficiently inferring correct drainage crossings within a remarkably short time frame (0.268 ms). Furthermore, we perform a detailed profiling of our approach on GPU systems to analyze performance bottlenecks.