论文标题
学会从图像中采样最有用的培训补丁
Learning to Sample the Most Useful Training Patches from Images
论文作者
论文摘要
一些图像恢复任务（例如Demosaicing）需要艰难的培训样品来学习有效的模型。现有的方法试图通过手动收集包含足够硬样本的新培训数据集来解决此数据培训问题，但是，即使在一个图像中，仍然存在硬和简单的区域。在本文中，我们提出了一种称为PatchNet的数据驱动方法，该方法学会从图像中选择最有用的补丁以构建新的训练集，而不是手动或随机选择。我们表明，我们的简单想法会自动从大规模数据集中选择翔实的样本，从而在PSNR方面产生了令人惊讶的2.35DB概括增长。除了其出色的有效性外，PatchNet还具有资源友好，因为它仅在培训期间应用，因此在推断过程中不需要任何额外的计算成本。
Some image restoration tasks like demosaicing require difficult training samples to learn effective models. Existing methods attempt to address this data training problem by manually collecting a new training dataset that contains adequate hard samples, however, there are still hard and simple areas even within one single image. In this paper, we present a data-driven approach called PatchNet that learns to select the most useful patches from an image to construct a new training set instead of manual or random selection. We show that our simple idea automatically selects informative samples out from a large-scale dataset, leading to a surprising 2.35dB generalisation gain in terms of PSNR. In addition to its remarkable effectiveness, PatchNet is also resource-friendly as it is applied only during training and therefore does not require any additional computational cost during inference.
