Flexible Mixed Precision Quantization for Learned Image Compression
This work addresses the storage and deployment challenges for LIC models, offering a more efficient quantization approach, though it is incremental as it builds on prior quantization techniques.
The paper tackles the high computational costs of Learned Image Compression (LIC) models by proposing a Flexible Mixed Precision Quantization (FMPQ) method that assigns varying bit-widths to different layers, resulting in improved BD-Rate performance under similar model size constraints compared to existing quantization methods.
Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the computational complexity of LIC models. However, most existing works perform fixed-precision quantization which suffers from sub-optimal utilization of resources due to the varying sensitivity to quantization of different layers of a neural network. In this paper, we propose a Flexible Mixed Precision Quantization (FMPQ) method that assigns different bit-widths to different layers of the quantized network using the fractional change in rate-distortion loss as the bit-assignment criterion. We also introduce an adaptive search algorithm which reduces the time-complexity of searching for the desired distribution of quantization bit-widths given a fixed model size. Evaluation of our method shows improved BD-Rate performance under similar model size constraints compared to other works on quantization of LIC models. We have made the source code available at gitlab.com/viper-purdue/fmpq.