arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.10309cs.CVcs.AI
收藏

LC-NAS:点云网络的时延约束神经结构搜索

LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks

Visual Computing Center, KAUST(阿卜杜拉国王科技大学视觉计算中心)

Guohao Li, Mengmeng Xu, Silvio Giancola, Ali Thabet, Bernard Ghanem

摘要:

点云结构设计已成为三维深度学习的关键问题。存在几种努力来手动设计在点云任务(诸如分类、分割和检测)中具有高精度的架构。自动神经结构搜索(NAS)的最新进展最大限度地减少了网络设计中的人力投入,并优化了高性能架构。然而,这些努力未能考虑重要因素,如推理过程中的延迟。延迟在自动驾驶汽车、机器人导航和移动应用等时间关键型应用中非常重要,这些应用通常受到可用硬件的限制。在本文中,我们介绍了一个新的NAS框架,被称为LC-NAS,在这里我们搜索的点云架构,限制到一个目标延迟。我们实现了一种新的延迟约束制定我们的架构搜索的准确性和延迟之间的权衡。与以前的工作相反,我们的延迟损失保证了最终网络在指定的目标值下实现延迟。当最终任务要部署在有限的硬件环境中时,这是至关重要的。大量的实验表明,LC-NAS能够以最小的计算成本在ModelNet 40中找到最先进的点云分类架构。我们还展示了我们搜索的架构如何以合理的低精度下降实现任何期望的延迟。最后,我们展示了我们搜索到的架构如何轻松地转移到不同的任务,即PartNet上的零件分割,在这里我们实现了最先进的结果,同时将延迟降低了10倍。

英文摘要:

Point cloud architecture design has become a crucial problem for 3D deep learning. Several efforts exist to manually design architectures with high accuracy in point cloud tasks such as classification, segmentation, and detection. Recent progress in automatic Neural Architecture Search (NAS) minimizes the human effort in network design and optimizes high performing architectures. However, these efforts fail to consider important factors such as latency during inference. Latency is of high importance in time critical applications like self-driving cars, robot navigation, and mobile applications, that are generally bound by the available hardware. In this paper, we introduce a new NAS framework, dubbed LC-NAS, where we search for point cloud architectures that are constrained to a target latency. We implement a novel latency constraint formulation to trade-off between accuracy and latency in our architecture search. Contrary to previous works, our latency loss guarantees that the final network achieves latency under a specified target value. This is crucial when the end task is to be deployed in a limited hardware setting. Extensive experiments show that LC-NAS is able to find state-of-the-art architectures for point cloud classification in ModelNet40 with minimal computational cost. We also show how our searched architectures achieve any desired latency with a reasonably low drop in accuracy. Finally, we show how our searched architectures easily transfer to a different task, part segmentation on PartNet, where we achieve state-of-the-art results while lowering latency by a factor of 10.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑