Cross-domain collaborative learning for single image deraining

Abstract

Deep Convolutional Neural Networks (DCNN) have achieved outstanding performance in image deraining tasks. However, current most methods regard rain streak removal as a one-to-one problem, and intra domain shift of different synthetic datasets is usually ignored. Therefore, the deraining models trained on one synthetic dataset cannot effectively remove the rain streak of other synthetic datasets. Also, image deraining models which are trained on the labeled synthetic datasets mostly suffer from performance degradation when tested on the unlabeled real datasets due to the inter domain gap. To address this issue, this paper proposes a Cross-Domain Collaborative Learning (CDCL) framework to minimize the intra domain shift and inter domain gap. Firstly, a dual branch deraining network with collaborative learning is proposed to eliminate the distribution shift of rain streaks of images within synthetic domains. Then, a Cross-Domain Pseudo Label Generation (CDPLG) method is designed to obtain more accurate and robust pseudo labels for real-world rainy images, and the online generated pseudo labels are utilized to train the dual branch deraining network for reducing the domain gap between synthetic domain and real domain. Extensive experiments are conducted on the public benchmark datasets including synthetic datasets and real datasets in image deraining, and experimental results demonstrate that our proposed framework performs favorably compared with the state-of-the-art models.