用Z-score归一化压缩机器间特征数据，显著降码率且不损失任务精度。
Efficient Feature Compression for Machines with Global Statistics Preservation
- 采用Z-score归一化实现特征数据高效压缩与还原
- 平均降低17.09%码率，物体追踪最高降65.69%且精度不变
- 适用于需要低延迟传输的分布式AI系统
分阶段推理范式将人工智能模型分为两部分，需在两部分间传输中间特征数据。有效压缩这些特征数据至关重要。本文提出使用Z-score归一化，在解码端高效恢复压缩后的特征数据。为验证方法有效性，将该方法集成至正在开发中的运动图像专家组（MPEG）最新机器特征编码标准（FCM）。相比当前标准使用的缩放方法，本方法在降低比特开销的同时提升端到端任务精度。为进一步减少特定场景下的开销，还提出简化版本。实验表明，所提方法在不同任务上平均码率降低17.09%，在物体追踪任务中最高降低65.69%，且未牺牲任务精度。
原文摘要 · Abstract (English)
The split-inference paradigm divides an artificial intelligence (AI) model into two parts. This necessitates the transfer of intermediate feature data between the two halves. Here, effective compression of the feature data becomes vital. In this paper, we employ Z-score normalization to efficiently recover the compressed feature data at the decoder side. To examine the efficacy of our method, the proposed method is integrated into the latest Feature Coding for Machines (FCM) codec standard under development by the Moving Picture Experts Group (MPEG). Our method supersedes the existing scaling method used by the current standard under development. It both reduces the overhead bits and improves the end-task accuracy. To further reduce the overhead in certain circumstances, we also propose a simplified method. Experiments show that using our proposed method shows 17.09% reduction in bitrate on average across different tasks and up to 65.69% for object tracking without sacrificing the task accuracy.
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。