面向人类与机器的可扩展编码中的条件与残差方法
Conditional and Residual Methods in Scalable Coding for Humans and Machines
AI总结:
本文研究面向人类与机器的可扩展编码,提出条件编码与残差编码方法,利用视觉任务信息优化重建率失真性能,并设计高建模能力的熵模型,在Cityscapes和COCO数据集上验证了两种方法的有效性。
摘要:
我们提出了在面向人类与机器的可扩展编码背景下的条件编码与残差编码方法。我们的重点是利用计算机视觉任务中可用的信息来优化重建任务的率失真性能。我们对这两种方法进行了信息分析,以提供基线,同时提出了一种适用于条件编码的熵模型,该模型具有比以往工作更高的建模能力,并保持相似的可处理性。我们将这些方法应用于图像重建:在一个实例中使用为Cityscapes数据集上的语义分割创建的表示,在另一个实例中使用为COCO数据集上的目标检测创建的表示。在两个实验中,条件方法与残差方法取得了相似的性能,所得的率失真曲线均包含在我们给出的基线范围内。
英文摘要:
We present methods for conditional and residual coding in the context of scalable coding for humans and machines. Our focus is on optimizing the rate-distortion performance of the reconstruction task using the information available in the computer vision task. We include an information analysis of both approaches to provide baselines and also propose an entropy model suitable for conditional coding with increased modelling capacity and similar tractability as previous work. We apply these methods to image reconstruction, using, in one instance, representations created for semantic segmentation on the Cityscapes dataset, and in another instance, representations created for object detection on the COCO dataset. In both experiments, we obtain similar performance between the conditional and residual methods, with the resulting rate-distortion curves contained within our baselines.
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。