SC2基准：面向分割计算的监督压缩
SC2 Benchmark: Supervised Compression for Split Computing
AI总结：
本文提出面向分割计算的监督压缩（SC2）基准，定义最小化设备计算、最小化传输数据和最大化精度的评估标准，并通过10种基线方法、三个视觉任务和180多个模型进行系统评测，同时发布sc2bench工具包。
摘要：
随着移动设备上深度学习模型需求的日益增长，在设备与更强大的边缘服务器之间分割神经网络计算已成为一种有吸引力的解决方案。然而，现有的分割计算方法与在压缩数据上进行远程计算的朴素基线相比往往表现不佳。近期研究提出学习包含更多与监督下游任务相关信息的压缩表示，展示了压缩数据大小与监督性能之间更好的权衡。然而，现有评估指标仅能提供分割计算的不完整图景。本研究引入面向分割计算的监督压缩（SC2），并提出新的评估标准：最小化移动设备上的计算量、最小化传输数据大小以及最大化模型精度。我们使用10种基线方法、三个计算机视觉任务和超过180个训练模型进行了全面的基准研究，并讨论了SC2的各个方面。我们还发布了sc2bench，一个用于未来SC2研究的Python软件包。我们提出的指标和软件包将帮助研究人员更好地理解分割计算中监督压缩的权衡。
英文摘要：
With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution. However, existing split computing approaches often underperform compared to a naive baseline of remote computation on compressed data. Recent studies propose learning compressed representations that contain more relevant information for supervised downstream tasks, showing improved tradeoffs between compressed data size and supervised performance. However, existing evaluation metrics only provide an incomplete picture of split computing. This study introduces supervised compression for split computing (SC2) and proposes new evaluation criteria: minimizing computation on the mobile device, minimizing transmitted data size, and maximizing model accuracy. We conduct a comprehensive benchmark study using 10 baseline methods, three computer vision tasks, and over 180 trained models, and discuss various aspects of SC2. We also release sc2bench, a Python package for future research on SC2. Our proposed metrics and package will help researchers better understand the tradeoffs of supervised compression in split computing.
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。
