Efficient Feature Compression for Machines with Global Statistics Preservation

2025-12-09

AI Summary

To address the bandwidth bottleneck in AI model split inference caused by intermediate feature transmission, this paper proposes a lightweight, lossless feature compression method based on Z-score normalization. The core innovation lies in the first integration of Z-score standardization into a feature compression framework to explicitly preserve global statistical properties—namely, mean and variance—enabling an end-to-end differentiable encoding architecture. Unlike the conventional scaling scheme in the MPEG FCM standard draft, our approach yields a more compact and hardware-efficient implementation. Extensive evaluation across multiple vision tasks demonstrates an average bitrate reduction of 17.09%, with up to 65.69% savings in object tracking, while maintaining zero accuracy degradation in downstream tasks.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

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.

Problem

• Compress intermediate feature data in split AI inference
• Improve compression efficiency while preserving global statistics
• Reduce bitrate without sacrificing end-task accuracy

Innovation

• Uses Z-score normalization for feature data recovery
• Integrates into MPEG's FCM codec standard
• Reduces bitrate while maintaining task accuracy