Search

Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution (SR). These CNN networks effectively recover a high-resolution (HR) image from a low-resolution (LR) image, at the cost of enormous parameters and heavy computational burden. In this work, we propose a recursive efficient deep convolutional network for fast and accurate single-image SR with only 0.28M parameters. A Split-Concatenate-Residual (SCR) block is proposed to reduce computation and parameters. With downsampling block and upsampling block, we significantly reduce computational complexity and enlarge the size of the receptive field. Specifically, two-level recursive learning is proposed which can improve accuracy by increasing depth without adding any weight parameters. We also employ local, semi-global and global residual techniques to train our very deep network steadily and improve its performance. Extensive experiments indicate that our proposed method Split-Concatenate-Residual Super Resolution (SCRSR) yields promising SR performance while maintaining shorter running time and fewer parameters. [ABSTRACT FROM AUTHOR]

Recently, inspired by the power of deep learning, convolution neural networks can produce fantastic images at the pixel level. However, a significant limiting factor for previous approaches is that they focus on some simple datasets such as faces and bedrooms. In this paper, we propose a multiscale deep neural network to transform sketches into Chinese paintings. To synthesize more realistic imagery, we train the generative network by using both L1 loss and adversarial loss. Additionally, users can control the process of the synthesis since the generative network is feed-forward. This network can also be treated as neural style transfer by adding an edge detector. Furthermore, additional experiments on image colorization and image super-resolution demonstrate the universality of our proposed approach. [ABSTRACT FROM AUTHOR]

In recent years, convolutional neural networks (CNNs) have shown great success in the scene classification of computer vision images. Although these CNNs can achieve excellent classification accuracy, the discriminative ability of feature representations extracted from CNNs is still limited in distinguishing more complex remote sensing images. Therefore, we propose a unified feature fusion framework based on attention mechanism in this paper, which is called Deep Discriminative Representation Learning with Attention Map (DDRL-AM). Firstly, by applying Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm, attention maps associated with the predicted results are generated in order to make CNNs focus on the most salient parts of the image. Secondly, a spatial feature transformer (SFT) is designed to extract discriminative features from attention maps. Then an innovative two-channel CNN architecture is proposed by the fusion of features extracted from attention maps and the RGB (red green blue) stream. A new objective function that considers both center and cross-entropy loss are optimized to decrease the influence of inter-class dispersion and within-class variance. In order to show its effectiveness in classifying remote sensing images, the proposed DDRL-AM method is evaluated on four public benchmark datasets. The experimental results demonstrate the competitive scene classification performance of the DDRL-AM approach. Moreover, the visualization of features extracted by the proposed DDRL-AM method can prove that the discriminative ability of features has been increased. [ABSTRACT FROM AUTHOR]

Exploring large graphs is difficult due to their large size and semantic information such as node attributes. Extracting only a subgraph relevant to the user-specified nodes (called focus nodes) is an effective strategy for exploring a large graph. However, existing approaches following this strategy mainly focus on graph topology and do not fully consider node attributes, resulting in the lack of clear semantics in the extracted subgraphs. In this paper, we propose a novel approach called TS-Extractor that can extract a relevant subgraph around the user-selected focus nodes to help the user explore the large graph from a local perspective. By combining the graph topology and the user-selected node attributes, TS-Extractor can extract and visualize a connected subgraph that contains as many nodes sharing the same/similar attribute values with the focus nodes as possible, thereby providing the user with clear semantics. Based on TS-Extractor, we develop a Web-based graph exploration system that allows users to interactively extract, analyze and expand subgraphs. Through two case studies and a user study, we demonstrate the usability and effectiveness of TS-Extractor. [ABSTRACT FROM AUTHOR]

Link prediction is a task predicting whether there is a link between two nodes in a network. Traditional link prediction methods that assume handcrafted features (such as common neighbors) as the link's formation mechanism are not universal. Other popular methods tend to learn the link's representation, but they cannot represent the link fully. In this paper, we propose Edge-Nodes Representation Neural Machine (ENRNM), a novel method which can learn abundant topological features from the network as the link's representation to promote the formation of the link. The ENRNM learns the link's formation mechanism by combining the representation of edge and the representations of nodes on the two sides of the edge as link's full representation. To predict the link's existence, we train a fully connected neural network which can learn meaningful and abundant patterns. We prove that the features of edge and two nodes have the same importance in link's formation. Comprehensive experiments are conducted on eight networks, experiment results demonstrate that the method ENRNM not only exceeds plenty of state-of-the-art link prediction methods but also performs very well on diverse networks with different structures and characteristics. [ABSTRACT FROM AUTHOR]

The spatial resolution and clarity of remote sensing images are crucial for many applications such as target detection and image classification. In the last several decades, tremendous image restoration tasks have shown great success in ordinary images. However, since remote sensing images are more complex and more blurry than ordinary images, most of the existing methods are not good enough for remote sensing image restoration. To address such problem, we propose a novel method named deep memory connected network (DMCN) based on the convolutional neural network to reconstruct high-quality images. We build local and global memory connections to combine image detail with global information. To further reduce parameters and ease time consumption, we propose Downsampling Units, shrinking the spatial size of feature maps. We verify its capability on two representative applications, Gaussian image denoising and single image super-resolution (SR). DMCN is tested on three remote sensing datasets with various spatial resolution. Experimental results indicate that our method yields promising improvements and better visual performance over the current state-of-the-art. The PSNR and SSIM improvements over the second best method are up to 0.3 dB. [ABSTRACT FROM AUTHOR]