Training-Free Adaptive Quantization for Variable Rate Image Coding for Machines
This addresses the practical limitation of fixed-rate ICM frameworks for computer vision applications, offering a more flexible and efficient solution.
The paper tackles the problem of variable rate control in Image Coding for Machines (ICM) by proposing a training-free adaptive quantization scheme, achieving up to 11.07% BD-rate savings over non-adaptive methods.
Image Coding for Machines (ICM) has become increasingly important with the rapid integration of computer vision into real-world applications. However, most ICM frameworks utilize learned image compression (LIC) models that operate at a fixed rate and require separate training for each target bitrate, which may limit their practical applications. Existing variable rate LIC approaches mitigate this limitation but typically depend on training, increasing computational cost and deployment complexity. Moreover, variable rate control has not been thoroughly explored for ICM. To address these challenges, we propose a training-free, adaptive quantization step size control scheme that enables flexible bitrate adjustment. By leveraging both channel-wise entropy dependencies and spatial scale parameters predicted by the hyperprior network, the proposed method preserves semantically important regions while coarsely quantizing less critical areas. The bitrate can be continuously controlled through a single parameter. Experimental results demonstrate the effectiveness of our proposed method, achieving up to 11.07% BD-rate savings over the non-adaptive variable rate method.