Rain streaks in an image appear in different sizes and orientations, resulting in severe blurring and visual quality degradation. Previous CNN-based algorithms have achieved encouraging deraining results although there are certain limitations in the description of rain streaks and the restoration of scene structures in different environments. In this paper, we propose an efficient multi-scale enhancement and aggregation network (MEAN) to solve the single-image deraining problem. Considering the importance of large receptive fields and multi-scale features, we introduce a multi-scale enhanced unit (MEU) to capture long-range dependencies and exploit features at different scales to depict rain. Simultaneously, an attentive aggregation unit (AAU) is designed to utilize the informative features in spatial and channel dimensions, thereby aggregating effective information to eliminate redundant features for rich scenario details. To improve the deraining performance of the encoder--decoder network, we utilized an AAU to filter the information in the encoder network and concatenated the useful features to the decoder network, which is conducive to predicting high-quality clean images. Experimental results on synthetic datasets and real-world samples show that the proposed method achieves a significant deraining performance compared to state-of-the-art approaches.

This paper proposes a kernel-blending connection approximated by a neural network (KBNN) for image classification. A kernel mapping connection structure, guaranteed by the function approximation theorem, is devised to blend feature extraction and feature classification through neural network learning. First, a feature extractor learns features from the raw images. Next, an automatically constructed kernel mapping connection maps the feature vectors into a feature space. Finally, a linear classifier is used as an output layer of the neural network to provide classification results. Furthermore, a novel loss function involving a cross-entropy loss and a hinge loss is proposed to improve the generalizability of the neural network. Experimental results on three well-known image datasets illustrate that the proposed method has good classification accuracy and generalizability.