Neural-based image and video codecs are significantly more power-efficient when weights and activations are quantized to low-precision integers. While there are general-purpose techniques for reducing quantization effects, large losses can occur when specific entropy coding properties are not considered. This work analyzes how entropy coding is affected by parameter quantizations, and provides a method to minimize losses. It is shown that, by using a certain type of coding parameters to be learned, uniform quantization becomes practically optimal, also simplifying the minimization of code memory requirements. The mathematical properties of the new representation are presented, and its effectiveness is demonstrated by coding experiments, showing that good results can be obtained with precision as low as 4~bits per network output, and practically no loss with 8~bits.
翻译:以神经为基础的图像和视频编码在将重量和激活量量化为低精度整数时,其功率效率要高得多。虽然有降低量化效应的通用技术,但当不考虑特定的酶编码特性时,可能会发生大量损失。这项工作分析了酶编码如何受到参数定量化的影响,并提供了尽量减少损失的方法。它表明,通过使用某种需要学习的编码参数,统一定量化实际上变得最佳,也简化了代码内存要求的最小化。介绍了新表示法的数学特性,并通过编码实验证明了其有效性,表明精确到每网络输出4位位位数的精确度可以取得良好的结果,8位位数实际上没有损失。