Learning to Sample the Most Useful Training Patches from Images

arxiv(2020)

引用 4|浏览51
暂无评分
摘要
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.
更多
查看译文
关键词
useful training patches,learning,sample
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要