Learning to Sample the Most Useful Training Patches from Images
This work addresses the problem of effectively selecting training data for image restoration tasks, which is beneficial for researchers and practitioners working on these problems.
This paper introduces PatchNet, a data-driven approach that learns to select the most useful training patches from images for restoration tasks. This method automatically selects informative samples, achieving a 2.35dB PSNR generalization gain.
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.