Multi-scale attention network for image super-resolution

The power of convolutional neural networks (CNN) has demonstrated irreplaceable advantages in super-resolution. However, many CNN-based methods need large model sizes to achieve superior performance, making them difficult to apply in the practical world with limited memory footprints. To efficiently balance model complexity and performance, we propose a multi-scale attention network (MSAN) by cascading multiple multi-scale attention blocks (MSAB), each of which integrates a multi-scale cross block (MSCB) and a multi-path wide-activated attention block (MWAB). Specifically, MSCB initially connects three parallel convolutions with different dilation rates hierarchically to aggregate the knowledge of features at different levels and scales. Then, MWAB split the channel features from MSCB into three portions to further improve performance. Rather than being treated equally and independently, each portion is responsible for a specific function, enabling internal communication among channels. Experimental results show that our MSAN outperforms most state-of-the-art methods with relatively few parameters and Mult-Adds.     

Fine-grained neural architecture search for image super-resolution

Designing efficient deep neural networks has achieved great interest in image super-resolution (SR). However, exploring diverse network structures is computationally expensive. More importantly, each layer in a network has a distinct role that leads to the design of a specialized structure. In this work, we present a novel neural architecture search (NAS) algorithm that efficiently explores layer-wise structures. Specifically, we construct a supernet allowing flexibility in choosing the number of channels and per-channel activation functions according to the role of each layer. The search process runs efficiently via channel pruning since gradient descent jointly optimizes the Mult-Adds and the accuracy of the searched models. We facilitate estimating the model Mult-Adds in a differentiable manner using relaxations in the backward pass. The searched model, named FGNAS, outperforms the state-of-the-art NAS-based SR methods by a large margin.     

Single image deraining using multi-scales context information and attention network

The existing deraining methods based on convolutional neural networks (CNNs) have made great success, but some remaining rain streaks can degrade images drastically. In this work, we proposed an end-to-end multi-scale context information and attention network, called MSCIANet. The proposed network consists of multi-scale feature extraction (MSFE) and multi-receptive fields feature extraction (MRFFE). Firstly, the MSFE can pick up features of rain streaks in different scales and propagate deep features of the two layers across stages by skip connections. Secondly, the MRFFE can refine details of the background by attention mechanism and the depthwise separable convolution of different receptive fields with different scales. Finally, the fusion of these outputs of two subnetworks can reconstruct the clean background image. Extensive experimental results have shown that the proposed network achieves a good effect on the deraining task on synthetic and real-world datasets. The demo can be available at https://github.com/CoderLi365/MSCIANet.     

Detail retaining convolutional neural network for image denoising

Compared with the traditional image denoising method, although the convolutional neural network (CNN) has better denoising performance, there is an important issue that has not been well resolved: the residual image obtained by learning the difference between noisy image and clean image pairs contains abundant image detail information, resulting in the serious loss of detail in the denoised image. In this paper, in order to relearn the lost image detail information, a mathematical model is deducted from a minimization problem and an end-to-end detail retaining CNN (DRCNN) is proposed. Unlike most denoising methods based on CNN, DRCNN is not only focus to image denoising, but also the integrity of high frequency image content. DRCNN needs less parameters and storage space, therefore it has better generalization ability. Moreover, DRCNN can also adapt to different image restoration tasks such as blind image denoising, single image superresolution (SISR), blind deburring and image inpainting. Extensive experiments show that DRCNN has a better effect than some classic and novel methods.     

MRANet: Multi-atrous residual attention Network for stereo image super-resolution

In recent years, stereo cameras have been widely used in various fields. Due to the limited resolution of real equipments, stereo image super-resolution (SR) is a very important and hot topic. Recent studies have shown that deep network structures can directly affect feature expression and extraction and thus influence the final results. In this paper, we propose a multi-atrous residual attention stereo super-resolution network (MRANet) with parallax extraction and strong discriminative ability. Specifically, we propose a multi-scale atrous residual attention (MARA) block to obtain receptive fields of different scales through a multi-scale atrous convolution and then combine them with attention mechanisms to extract more diverse and meaningful information. Moreover, we propose a stereo feature fusion unit for stereo parallax extraction and single viewpoint feature refinement and integration. Experiments on benchmark datasets show that MRANet achieves state-of-the-art performance in terms of quantitative metrics and visual quality compared with several SR methods.     

Contour enhanced image super-resolution

Recently, very deep convolution neural network (CNN) has shown strong ability in single image super-resolution (SISR) and has obtained remarkable performance. However, most of the existing CNN-based SISR methods rarely explicitly use the high-frequency information of the image to assist the image reconstruction, thus making the reconstructed image looks blurred. To address this problem, a novel contour enhanced Image Super-Resolution by High and Low Frequency Fusion Network (HLFN) is proposed in this paper. Specifically, a contour learning subnetwork is designed to learn the high-frequency information, which can better learn the texture of the image. In order to reduce the redundancy of the contour information learned by the contour learning subnetwork during fusion, the spatial channel attention block (SCAB) is introduced, which can select the required high-frequency information adaptively. Moreover, a contour loss is designed and it is used with the $\ell 1$ loss to optimize the network jointly. Comprehensive experiments demonstrate the superiority of our HLFN over state-of-the-art SISR methods.     

Research on image feature extraction and retrieval algorithms based on convolutional neural network

With the rapid development of mobile Internet and digital technology, people are more and more keen to share pictures on social networks, and online pictures have exploded. How to retrieve similar images from large-scale images has always been a hot issue in the field of image retrieval, and the selection of image features largely affects the performance of image retrieval. The Convolutional Neural Networks (CNN), which contains more hidden layers, has more complex network structure and stronger ability of feature learning and expression compared with traditional feature extraction methods. By analyzing the disadvantage that global CNN features cannot effectively describe local details when they act on image retrieval tasks, a strategy of aggregating low-level CNN feature maps to generate local features is proposed. The high-level features of CNN model pay more attention to semantic information, but the low-level features pay more attention to local details. Using the increasingly abstract characteristics of CNN model from low to high. This paper presents a probabilistic semantic retrieval algorithm, proposes a probabilistic semantic hash retrieval method based on CNN, and designs a new end-to-end supervised learning framework, which can simultaneously learn semantic features and hash features to achieve fast image retrieval. Using convolution network, the error rate is reduced to 14.41% in this test set. In three open image libraries, namely Oxford, Holidays and ImageNet, the performance of traditional SIFT-based retrieval algorithms and other CNN-based image retrieval algorithms in tasks are compared and analyzed. The experimental results show that the proposed algorithm is superior to other contrast algorithms in terms of comprehensive retrieval effect and retrieval time.     

NERNet: Noise estimation and removal network for image denoising

While some denoising methods based on deep learning achieve superior results on synthetic noise, they are far from dealing with photographs corrupted by realistic noise. Denoising on real-world noisy images faces more significant challenges due to the source of it is more complicated than synthetic noise. To address this issue, we propose a novel network including noise estimation module and removal module (NERNet). The noise estimation module automatically estimates the noise level map corresponding to the information extracted by symmetric dilated block and pyramid feature fusion block. The removal module focuses on removing the noise from the noisy input with the help of the estimated noise level map. Dilation selective block with attention mechanism in the removal module adaptively not only fuses features from convolution layers with different dilation rates, but also aggregates the global and local information, which is benefit to preserving more details and textures. Experiments on two datasets of synthetic noise and three datasets of realistic noise show that NERNet achieves competitive results in comparison with other state-of-the-art methods.     

CCNet: CNN model with channel attention and convolutional pooling mechanism for spatial image steganalysis

Image steganalysis based on convolutional neural networks(CNN) has attracted great attention. However, existing networks lack attention to regional features with complex texture, which makes the ability of discrimination learning miss in network. In this paper, we described a new CNN designed to focus on useful features and improve detection accuracy for spatial-domain steganalysis. The proposed model consists of three modules: noise extraction module, noise analysis module and classification module. A channel attention mechanism is used in the noise extraction module and analysis module, which is realized by embedding the SE(Squeeze-and-Excitation) module into the residual block. Then, we use convolutional pooling instead of average pooling to aggregate features. The experimental results show that detection accuracy of the proposed model is significantly better than those of the existing models such as SRNet, Zhu-Net and GBRAS-Net. Compared with these models, our model has better generalization ability, which is critical for practical application.     

采用精简卷积神经网络的快速视频超分辨率重建

超分辨率重建在视频的传输和显示中起着重要的 作用。为了既保证重建视频的清晰度,又面向用户 实时显示,提出了一种采用精简卷积神经网络的快速视频超分辨率重建方法。所提的精简卷 积神经网络体 现在以下三点:首先,考虑到输入的尺寸大小会直接影响网络的运算速度,所提网络省去传 统方法的预插 值过程,直接对多个低分辨率输入视频帧提取特征,并进行多维特征通道融合。接着,为了 避免网络中产 生零梯度而丢失视频的重要信息,采用参数线性纠正单元(Parametric Rectified Linear Unit,PReLU)作为激 活函数,并采用尺寸更小的滤波器调整网络结构以进行多层映射。最后,在网络末端添加反 卷积层上采样 得到重建视频。实验结果显示,所提方法相比有代表性的方法在PSNR和SSIM指 标上分别平均 提升了0.32dB和0.016,同时在 GPU下达到平均41帧/秒的重建速度。结果表明所提方法可快速重建质 量更优的视频。     

基于门控卷积神经网络的图像超分辨重建算法北大核心CSCD

近年来,卷积神经网络被广泛应用于图像超分辨率领域。针对基于卷积神经网络的超分辨率算法存在图像特征提取不充分,参数量大和训练难度大等问题,本文提出了一种基于门控卷积神经网络(gated convolutional neural network, GCNN)的轻量级图像超分辨率重建算法。首先,通过卷积操作对原始低分辨率图像进行浅层特征提取。之后,通过门控残差块(gated residual block, GRB)和长短残差连接充分提取图像特征,其高效的结构也能加速网络训练过程。GRB中的门控单元(gated unit, GU)使用区域自注意力机制提取输入特征图中的每个特征点权值,紧接着将门控权值与输入特征逐元素相乘作为GU输出。最后,使用亚像素卷积和卷积模块重建出高分辨率图像。在Set14、BSD100、Urban100和Manga109数据集上进行实验,并和经典方法进行对比,本文算法有更高的峰值信噪比(peak signal-to-noise ratio,PSNR)和结构相似性(structural similarity,SSIM),重建出的图像有更清晰的轮廓边缘和细节信息。     

Screen content image quality assessment based on convolutional neural networks

Screen content image (SCI) is a composite image including textual and pictorial regions resulting in many difficulties in image quality assessment (IQA). Large SCIs are divided into image patches to increase training samples for CNN training of IQA model, and this brings two problems: (1) local quality of each image patch is not equal to subjective differential mean opinion score (DMOS) of an entire image; (2) importance of different image patches is not same for quality assessment. In this paper, we propose a novel no-reference (NR) IQA model based on the convolutional neural network (CNN) for assessing the perceptual quality of SCIs. Our model conducts two designs solving problems which benefits from two strategies. For the first strategy, to imitate full-reference (FR) CNN-based model behavior, a CNN-based model is designed for both FR and NR IQA, and performance of NR-IQA part improves when the image patch scores predicted by FR-IQA part are adopted as the ground-truth to train NR-IQA part. For the second strategy, image patch qualities of one entire SCI are fused to obtain the SCI quality with an adaptive weighting method taking account the effect of the different image patch contents. Experimental results verify that our model outperforms all test NR IQA methods and most FR IQA methods on the screen content image quality assessment database (SIQAD). On the cross-database evaluation, the proposed method outperforms the existing NR IQA method in terms of at least 2.4 percent in PLCC and 2.8 percent in SRCC, which shows high generalization ability and high effectiveness of our model.     

Speckle noise removal based on structural convolutional neural networks with feature fusion for medical image

Application of convolutional neural networks (CNNs) for image additive white Gaussian noise (AWGN) removal has attracted considerable attentions with the rapid development of deep learning in recent years. However, the work of image multiplicative speckle noise removal is rarely done. Moreover, most of the existing speckle noise removal algorithms are based on traditional methods with human priori knowledge, which means that the parameters of the algorithms need to be set manually. Nowadays, deep learning methods show clear advantages on image feature extraction. Multiplicative speckle noise is very common in real life images, especially in medical images. In this paper, a novel neural network structure is proposed to recover noisy images with speckle noise. Our proposed method mainly consists of three subnetworks. One network is rough clean image estimate subnetwork. Another is subnetwork of noise estimation. The last one is an information fusion network based on U-Net and several convolutional layers. Different from the existing speckle denoising model based on the statistics of images, the proposed network model can handle speckle denoising of different noise levels with an end-to-end trainable model. Extensive experimental results on several test datasets clearly demonstrate the superior performance of our proposed network over state-of-the-arts in terms of quantitative metrics and visual quality.     

Screen-shooting resistant image watermarking based on lightweight neural network in frequency domain

Currently, digital mobile devices, especially smartphones, can be used to acquire information conveniently through photograph taking. To protect information security in this case, we propose an efficient screen-shooting resistant watermarking scheme via deep neural network (DNN) in the frequency domain to achieve additional information embedding and source tracing. Specifically, we enhance the imperceptibility of watermarked images and the robustness against various attacks in real scene by computing the residual watermark message and encoding it with the original image using a lightweight neural network in the DCT domain. In addition, a noise layer is designed to simulate the photometric and radiometric effects of screen-shooting transfer. During the training process, the enhancing network is used to highlight the coding features of distorted images and improve the accuracy of extracted watermark message. Experimental results demonstrate that our scheme not only effectively ensures the balance between the imperceptibility of watermark embedding and the robustness of watermark extraction, but also significantly improves computational efficiency compared with some state-of-the-art schemes.     

Large scale automatic image annotation based on convolutional neural network

Automatic image annotation is one of the most important challenges in computer vision, which is critical to many real-world researches and applications. In this paper, we focus on the issue of large scale image annotation with deep learning. Firstly, considering the existing image data, especially the network images, most of the labels of themselves are inaccurate or imprecise. We propose a Multitask Voting (MV) method, which can improve the accuracy of original annotation to a certain extent, thereby enhancing the training effect of the model. Secondly, the MV method can also achieve the adaptive label, whereas most existing methods pre-specify the number of tags to be selected. Additionally, based on convolutional neural network, a large scale image annotation model MVAIACNN is constructed. Finally, we evaluate the performance with experiments on the MIRFlickr25K and NUS-WIDE datasets, and compare with other methods, demonstrating the effectiveness of the MVAIACNN.     

S&CNet: A lightweight network for fast and accurate depth completion

Dense depth completion is essential for autonomous driving and robotic navigation. Existing methods focused on attaining higher accuracy of the estimated depth, which comes at the price of increasing complexity and cannot be well applied in a real-time system. In this paper, a coarse-to-fine and lightweight network (S&CNet) is proposed for dense depth completion to reduce the computational complexity with negligible sacrifice on accuracy. A dual-stream attention module (S&C enhancer) is proposed according to a new finding of deep neural network-based depth completion, which can capture both the spatial-wise and channel-wise global-range information of extracted features efficiently. Then it is plugged between the encoder and decoder of the coarse estimation network so as to improve the performance. The experiments on KITTI dataset demonstrate that the proposed approach achieves competitive result with respect to state-of-the-art works but via an almost four times faster speed. The S&C enhancer can also be easily plugged into other existing works to boost their performances significantly with negligible additional computations.     

EEG-based prediction of driver's cognitive performance by deep convolutional neural network

We considered the prediction of driver's cognitive states related to driving performance using EEG signals. We proposed a novel channel-wise convolutional neural network (CCNN) whose architecture considers the unique characteristics of EEG data. We also discussed CCNN-R, a CCNN variation that uses Restricted Boltzmann Machine to replace the convolutional filter, and derived the detailed algorithm. To test the performance of CCNN and CCNN-R, we assembled a large EEG dataset from 3 studies of driver fatigue that includes samples from 37 subjects. Using this dataset, we investigated the new CCNN and CCNN-R on raw EEG data and also Independent Component Analysis (ICA) decomposition. We tested both within-subject and cross-subject predictions and the results showed CCNN and CCNN-R achieved robust and improved performance over conventional DNN and CNN as well as other non-DL algorithms.     

Image source identification with known post-processed based on convolutional neural network

Image source identification is important to verify the origin and authenticity of digital images. However, when images are altered by some post-processing, the performance of the existing source verification methods may degrade. In this paper, we propose a convolutional neural network (CNN) to solve the above problem. Specifically, we present a theoretical framework for different tampering operations, to confirm whether a single operation has affected photo response non-uniformity (PRNU) contained in images. Then, we divide these operations into two categories: non-influential operation and influential operation. Besides, the images altered by the combination of non-influential and influential operations are equal to images that have only undergone a single influential operation. To make our introduced CNN robust to both non-influential operation and influential operation, we define a multi-kernel noise extractor that consists of a high-pass filter and three parallel convolution filters of different sizes. The features generated by the parallel convolution layers are then fed to subsequent convolutional layers for further feature extraction. The experimental results provide the effectiveness of our method.     

基于卷积神经网络和注意力机制的图像检索

当前先进的图像检索方法中,存在着不能很好地分辨图像中不同区域和内容的重要性的问题,导致计算资源分配不合理、检索正确率较低等一系列结果.为了解决这些问题,提出了一种基于卷积神经网络(Convolutional Neural Network,CNN)和注意力机制的图像检索方法.首先使用卷积神经网络提取特征,然后使用注意力机...