We sincerely thank our reviewers for the constructive feedback. R4), has strength in visual quality (R1, R3, R4), and performs diverse (R1) and thorough (R3, R4) experiments. Note that we do not claim to be the first to use swapping for disentanglement. We apologize for any confusion. Moreover, our method supports HD resolution (e.g. the mountain example Therefore, we believe our method has advantage over general texture transfer methods.

We sincerely thank our reviewers for the constructive feedback. R4), has strength in visual quality (R1, R3, R4), and performs diverse (R1) and thorough (R3, R4) experiments. Note that we do not claim to be the first to use swapping for disentanglement. We apologize for any confusion. Moreover, our method supports HD resolution (e.g. the mountain example Therefore, we believe our method has advantage over general texture transfer methods.

Deep learning in general focuses on training a neural network from large labeled datasets. Yet, in many cases there is value in training a network just from the input at hand. This may involve training a network from scratch using a single input or adapting an already trained network to a provided input example at inference time. This survey paper aims at covering deep internal-learning techniques that have been proposed in the past few years for these two important directions. While our main focus will be on image processing problems, most of the approaches that we survey are derived for general signals (vectors with recurring patterns that can be distinguished from noise) and are therefore applicable to other modalities. We believe that the topic of internal-learning is very important in many signal and image processing problems where training data is scarce and diversity is large on the one hand, and on the other, there is a lot of structure in the data that can be exploited.

In recent years, multi-scale generative adversarial networks (GANs) have been proposed to build generalized image processing models based on single sample. Constraining on the sample size, multi-scale GANs have much difficulty converging to the global optimum, which ultimately leads to limitations in their capabilities. In this paper, we pioneered the introduction of PAC-Bayes generalized bound theory into the training analysis of specific models under different adversarial training methods, which can obtain a non-vacuous upper bound on the generalization error for the specified multi-scale GAN structure. Based on the drastic changes we found of the generalization error bound under different adversarial attacks and different training states, we proposed an adaptive training method which can greatly improve the image manipulation ability of multi-scale GANs. The final experimental results show that our adaptive training method in this paper has greatly contributed to the improvement of the quality of the images generated by multi-scale GANs on several image manipulation tasks. In particular, for the image super-resolution restoration task, the multi-scale GAN model trained by the proposed method achieves a 100% reduction in natural image quality evaluator (NIQE) and a 60% reduction in root mean squared error (RMSE), which is better than many models trained on large-scale datasets.