论文标题
对内部预测的神经网络的迭代培训
Iterative training of neural networks for intra prediction
论文作者
论文摘要
本文介绍了对基于块的图像和视频编解码器中内部预测的神经网络的迭代培训。首先，神经网络是由图像的编解码分区引起的块训练的，每个块与其上下文配对。然后，迭代地，通过编解码器从图像的分配中收集块，包括在上一次迭代中训练的神经网络，每个神经网络与其上下文配对，并且神经网络在新对中进行重新训练。多亏了这项培训，神经网络可以学习内部预测功能，这些功能都从初始编解码器中已经脱颖而出，并从速率降低的方面促进编解码器。此外，迭代过程允许设计培训数据清洁对于神经网络培训所必需的。将迭代训练的神经网络放入H.265（HM-16.15）中时，获得平均DB率降低的-4.2％。通过将它们移至H.266（VTM-5.0）中，平均DB率降低达到-1.9％。
This paper presents an iterative training of neural networks for intra prediction in a block-based image and video codec. First, the neural networks are trained on blocks arising from the codec partitioning of images, each paired with its context. Then, iteratively, blocks are collected from the partitioning of images via the codec including the neural networks trained at the previous iteration, each paired with its context, and the neural networks are retrained on the new pairs. Thanks to this training, the neural networks can learn intra prediction functions that both stand out from those already in the initial codec and boost the codec in terms of rate-distortion. Moreover, the iterative process allows the design of training data cleansings essential for the neural network training. When the iteratively trained neural networks are put into H.265 (HM-16.15), -4.2% of mean dB-rate reduction is obtained. By moving them into H.266 (VTM-5.0), the mean dB-rate reduction reaches -1.9%.
