Codebook-Based Adaptive Feature Compression With Semantic Enhancement for Edge-Cloud Systems
This addresses the challenge of efficient image analysis in edge-cloud systems, offering a domain-specific improvement for low-bitrate scenarios.
The paper tackles the problem of compressing image features for edge-cloud systems under low-bitrate conditions, where existing methods perform poorly, and proposes CAFC-SE, which uses vector quantization and selective transmission to achieve superior rate-accuracy performance in experiments.
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.