PatchNR: Learning from Small Data by Patch Normalizing Flow Regularization. (arXiv:2205.12021v2 [cs.LG] UPDATED)

Learning neural networks using only a small amount of data is an important
ongoing research topic with tremendous potential for applications. In this
paper, we introduce a regularizer for the variational modeling of inverse
problems in imaging based on normalizing flows. Our regularizer, called
patchNR, involves a normalizing flow learned on patches of very few images. In
particular, the training is independent from the considered inverse problem
such that the same regularizer can be used for different forward operators
acting …

arxiv data flow learning lg regularization small small data