让低功耗设备也能用大模型，靠的是高效传输中间特征。
Enabling Next-Generation Consumer Experience with Feature Coding for Machines
- 将神经网络中间特征编码压缩，实现高效传输。
- 相比远程推理，比特率降低75.90%且精度不变。
- 适合智能终端、物联网设备等资源受限场景。
随着消费设备日益智能化和互联化，机器任务的高效数据传输解决方案变得至关重要。本文概述了最新推出的面向机器的特征编码（Feature Coding for Machines, FCM）标准，该标准属于MPEG-AI，由动态图像专家组（MPEG）开发。FCM通过支持中间神经网络特征的高效提取、压缩与传输，赋能人工智能驱动的应用。通过将计算密集型操作卸载至具备高算力的基座服务器，FCM使低功耗设备也能利用大型深度学习模型。实验结果表明，在保持相同精度的前提下，相较远程推理，FCM标准可将比特率降低75.90%。
原文摘要 · Abstract (English)
As consumer devices become increasingly intelligent and interconnected, efficient data transfer solutions for machine tasks have become essential. This paper presents an overview of the latest Feature Coding for Machines (FCM) standard, part of MPEG-AI and developed by the Moving Picture Experts Group (MPEG). FCM supports AI-driven applications by enabling the efficient extraction, compression, and transmission of intermediate neural network features. By offloading computationally intensive operations to base servers with high computing resources, FCM allows low-powered devices to leverage large deep learning models. Experimental results indicate that the FCM standard maintains the same level of accuracy while reducing bitrate requirements by 75.90% compared to remote inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。