为图像压缩模型设计可变精度量化，提升压缩效率
Flexible Mixed Precision Quantization for Learned Image Compression
- 按层分配不同比特位数，依据率失真损失变化率决定
- 在相同模型大小下，比现有方法降低1.2%以上BD-Rate
- 适合部署资源受限的图像压缩系统
尽管相比传统编码器，学习型图像压缩（LIC）在编码性能上有所提升，但其存储与部署的计算开销较大。模型量化是降低LIC模型复杂度的有效手段。然而，现有方法多采用固定精度量化，因网络各层对量化敏感度不同，导致资源利用不充分。本文提出灵活混合精度量化（FMPQ），以率失真损失的分数变化作为比特分配标准，为网络不同层分配不同比特位数。同时引入自适应搜索算法，显著降低在给定模型尺寸下寻找最优比特分布的时间复杂度。实验表明，在相同模型规模约束下，本方法相比其他量化LIC工作，实现了更低的BD-Rate。代码已公开于gitlab.com/viper-purdue/fmpq。
原文摘要 · Abstract (English)
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.
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。