用可学习码本压缩视觉特征，低比特下仍保持高分析精度。
Codebook-Based Adaptive Feature Compression With Semantic Enhancement for Edge-Cloud Systems
- 边缘侧用向量量化将连续特征映射为离散索引，减少传输数据量。
- 在低比特率下仍能保留关键视觉模式，准确率优于传统方法。
- 适合对带宽敏感、需高精度分析的边缘云系统场景。
在边缘云系统中，以极低码率编码图像并保持强分析性能至关重要。现有方法或在重建图像上进行分析，或对中间特征使用熵模型压缩后解码分析，但在低比特率下表现不佳，因保留冗余信息或符号分布过集中。本文提出基于码本的自适应特征压缩框架CAFC-SE，通过向量量化（VQ）将边缘侧的连续视觉特征映射为离散索引，并选择性传至云端。该操作将特征向量投影到最近的视觉原型，从而在低比特条件下更好地保留关键视觉模式，使系统更抗低比特冲击。大量实验表明，本方法在码率与准确率方面均具优势。
原文摘要 · Abstract (English)
Coding images for machines with minimal bitrate and strong analysis performance is key to effective edge-cloud systems. Several approaches deploy an image codec and perform analysis on the reconstructed image. Other methods compress intermediate features using entropy models and subsequently perform analysis on the decoded features. Nevertheless, these methods both perform poorly under low-bitrate conditions, as they retain many redundant details or learn over-concentrated symbol distributions. In this paper, we propose a Codebook-based Adaptive Feature Compression framework with Semantic Enhancement, named CAFC-SE. It maps continuous visual features to discrete indices with a codebook at the edge via Vector Quantization (VQ) and selectively transmits them to the cloud. The VQ operation that projects feature vectors onto the nearest visual primitives enables us to preserve more informative visual patterns under low-bitrate conditions. Hence, CAFC-SE is less vulnerable to low-bitrate conditions. Extensive experiments demonstrate the superiority of our method in terms of rate and 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。