arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.12367cs.CVcs.LGcs.MM
收藏

面向机器视频编码中实现内容特定滤波器的竞争学习

Competitive Learning for Achieving Content-specific Filters in Video Coding for Machines

Nokia Technologies(诺基亚技术公司)

Honglei Zhang, Jukka I. Ahonen, Nam Le, Ruiying Yang, Francesco Cricri

AI总结:

本文针对机器视觉任务的视频编码需求,提出基于竞争学习的内容特定后处理滤波器训练策略,在VVC框架下的实验验证了该方法能有效提升目标检测和实例分割任务的编码效率。

摘要:

本文研究了联合优化内容特定后处理滤波器,将面向人类的视频/图像编解码器适配为适用于机器视觉任务的编解码器的效能。通过观察到视频/图像编解码器产生的伪影具有内容依赖性,我们提出了一种基于竞争学习原理的新型训练策略。该策略以模糊方式将训练样本动态分配给滤波器,进一步优化给定样本上的获胜滤波器。受模拟退火优化技术的启发,我们采用带温度变量的softmax函数作为权重分配函数,以减轻随机初始化的影响。我们在一个在Versatile Video Coding(VVC,通用视频编码)编解码器框架内使用多个后处理滤波器的系统上进行了评估,结果表明,采用我们提出的策略训练的内容特定滤波器具有优越性,尤其是在对图像进行分块处理时。以VVC参考软件VTM 12.0作为锚点,在OpenImages数据集上的实验表明,与独立训练的滤波器相比,目标检测和实例分割任务的BD-rate降低幅度分别从-41.3%和-44.6%提升至-42.3%和-44.7%。滤波器使用情况的统计结果与我们的假设一致,凸显了针对内容和重建质量联合优化滤波器的重要性。我们的研究结果为进一步提升视频/图像编解码器的性能铺平了道路。

英文摘要:

This paper investigates the efficacy of jointly optimizing content-specific post-processing filters to adapt a human oriented video/image codec into a codec suitable for machine vision tasks. By observing that artifacts produced by video/image codecs are content-dependent, we propose a novel training strategy based on competitive learning principles. This strategy assigns training samples to filters dynamically, in a fuzzy manner, which further optimizes the winning filter on the given sample. Inspired by simulated annealing optimization techniques, we employ a softmax function with a temperature variable as the weight allocation function to mitigate the effects of random initialization. Our evaluation, conducted on a system utilizing multiple post-processing filters within a Versatile Video Coding (VVC) codec framework, demonstrates the superiority of content-specific filters trained with our proposed strategies, specifically, when images are processed in blocks. Using VVC reference software VTM 12.0 as the anchor, experiments on the OpenImages dataset show an improvement in the BD-rate reduction from -41.3% and -44.6% to -42.3% and -44.7% for object detection and instance segmentation tasks, respectively, compared to independently trained filters. The statistics of the filter usage align with our hypothesis and underscore the importance of jointly optimizing filters for both content and reconstruction quality. Our findings pave the way for further improving the performance of video/image codecs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑