Convolutional image deraining networks have achieved great success while suffering from tremendous computational and memory costs. Most model compression methods require original data for iterative fine-tuning, which is limited in real-world applications due to storage, privacy, and transmission constraints. We note that it is overstretched to fine-tune the compressed model using self-collected data, as it exhibits poor generalization over images with different degradation characteristics. To address this problem, we propose a novel data-free compression framework for de-raining networks. It is based on our observation that deep degradation representations can be clustered by degradation characteristics (types of rain) while independent of image content. Therefore, in our framework, we “dream” diverse in-distribution degraded images using a deep inversion paradigm, thus leveraging them to distill the pruned model. Specifically, we preserve the performance of the pruned model in a dual-branch way. In one branch, we invert the pre-trained model (teacher) to reconstruct the degraded inputs that resemble the original distribution and employ the orthogonal regularization for deep features to yield degradation diversity. In the other branch, the pruned model (student) is distilled to fit the teacher's original statistical modeling on these dreamed inputs. Further, an adaptive pruning scheme is proposed to determine the hierarchical sparsity, which alleviates the regression drift of the initial pruned model. Experiments on various deraining datasets demonstrate that our method can reduce about 40% FLOPs of the state-of-the-art models while maintaining comparable performance without original data.

Wavelength-dependent light absorption and scattering result in the color cast and contrast degradation, which degrades the visibility of underwater images. Deep-learning-based under-water image enhancement has made significant progress in recent years. However, existing algorithms rely heavily on massive data for training, and the difficulty of collecting massive data in real-world environments limits their applicability. To alleviate this problem, we propose a fast adaptive self-supervised underwater image enhancement method, which models the entire water domain in terms of color and contrast distribution with only a few images. Specifically, to learn the mapping of color correction and contrast enhancement, our framework contains two sub-networks: a Color Mapping Net (CLM-Net) and a Contrast Mapping Net (CTM-Net). The CLM-Net learns the color correction mapping under the constraint of gray world assumption in a self-supervised manner. Besides, the CTM-Net estimates the contrast enhancement mapping under the constraint of the dark channel prior. Thanks to adaptive self-supervised training, we can primarily alleviate the need for collecting massive data and achieve effective underwater image enhancement with only ten images. Experiments demonstrate that the proposed algorithm achieves state-of-the-art performance on four benchmark datasets.