Multi-receptive Field Aggregation Network for single image deraining

Image deraining is a significant problem that ensures the visual quality of images to prompt computer vision systems. However, due to the insufficiency of captured rain streaks features and global information, current image deraining methods often face the issues of rain streaks remaining and image blurring. In this paper, we propose a Multi-receptive Field Aggregation Network (MRFAN) to restore a cleaner rain-free image. Specifically, we construct a Multi-receptive Field Feature Extraction Block (MFEB) to capture rain features with different receptive fields. In MFEB, we design a Self-supervised Block (SSB) and an Aggregation Block (AGB). SSB can make the network adaptively focus on the critical rain features and rain-covered areas. AGB effectively aggregates and redistributes the multi-scale features to help the network simulate rain streaks better. Experiments show that our method achieves better results on both synthetic datasets and real-world rainy images.     

Single image deraining using Context Aggregation Recurrent Network

Single image deraining is a challenging problem due to the presence of non-uniform rain densities and the ill-posedness of the problem. Moreover, over-/under-deraining can directly impact the performance of vision systems. To address these issues, we propose an end-to-end Context Aggregation Recurrent Network, called CARNet, to remove rain streaks from single images. In this paper, we assume that a rainy image is the linear combination of a clean background image with rain streaks and propose to take advantage of the context information and feature reuse to learn the rain streaks. In our proposed network, we first use the dilation technique to effectively aggregate context information without sacrificing the spatial resolution, and then leverage a gated subnetwork to fuse the intermediate features from different levels. To better learn and reuse rain streaks, we integrate a LSTM module to connect different recurrences for passing the information learned from the previous stages about the rain streaks to the following stage. Finally, to further refine the coarsely derained image, we introduce a refinement module to better preserve image details. As for the loss function, the L1-norm perceptual loss and SSIM loss are adopted to reduce the gridding artifacts caused by the dilated convolution. Experiments conducted on synthetic and real rainy images show that our CARNet achieves superior deraining performance both qualitatively and quantitatively over the state-of-the-art approaches.     

Multi-scale convolutional attention network for lightweight image super-resolution

Convolutional neural network (CNN) based methods have recently achieved extraordinary performance in single image super-resolution (SISR) tasks. However, most existing CNN-based approaches increase the model’s depth by stacking massive kernel convolutions, bringing expensive computational costs and limiting their application in mobile devices with limited resources. Furthermore, large kernel convolutions are rarely used in lightweight super-resolution designs. To alleviate the above problems, we propose a multi-scale convolutional attention network (MCAN), a lightweight and efficient network for SISR. Specifically, a multi-scale convolutional attention (MCA) is designed to aggregate the spatial information of different large receptive fields. Since the contextual information of the image has a strong local correlation, we design a local feature enhancement unit (LFEU) to further enhance the local feature extraction. Extensive experimental results illustrate that our proposed MCAN can achieve better performance with lower model complexity compared with other state-of-the-art lightweight methods.     

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.     

基于注意力机制的多分支特征级联图像去雨网络

针对已有去雨网络在不同环境中去雨不彻底和图像细节信息损失严重的问题,本文提出一种基于注意力机制的多分支特征级联图像去雨网络。该模型结合多种注意力机制,形成不同类型的多分支网络,将图像空间细节和上下文特征信息在整体网络中自下而上地进行传递并级联融合,同时在网络分支间构建的阶段注意融合机制,可以减少特征提取过程中图像信息的损失,更大限度地保留特征信息,使图像去雨任务更加高效。实验结果表明,本文算法的客观评价指标优于其他对比算法,主观视觉效果得以有效提升,去雨能力更强,准确性更加突出,能够去除不同密度的雨纹,并且能够更好地保留图像背景中的细节信息。     

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.     

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.     

Multi-scale attention guided network for end-to-end face alignment and recognition

Attention modules embedded in deep networks mediate the selection of informative regions for object recognition. In addition, the combination of features learned from different branches of a network can enhance the discriminative power of these features. However, fusing features with inconsistent scales is a less-studied problem. In this paper, we first propose a multi-scale channel attention network with an adaptive feature fusion strategy (MSCAN-AFF) for face recognition (FR), which fuses the relevant feature channels and improves the network’s representational power. In FR, face alignment is performed independently prior to recognition, which requires the efficient localization of facial landmarks, which might be unavailable in uncontrolled scenarios such as low-resolution and occlusion. Therefore, we propose utilizing our MSCAN-AFF to guide the Spatial Transformer Network (MSCAN-STN) to align feature maps learned from an unaligned training set in an end-to-end manner. Experiments on benchmark datasets demonstrate the effectiveness of our proposed MSCAN-AFF and MSCAN-STN.     

基于改进生成对抗网络模型的红外与可见光图像融合

为增强融合图像的视觉效果,减少计算的复杂度,解决传统红外与可见光图像融合算法存在的背景细节丢失问题,提出了一种生成对抗网络框架下基于深度可分离卷积的红外与可见光图像融合方法。首先,在生成器中对源图像进行深度卷积与逐点卷积运算,得到源图像的特征映射信息;其次,通过前向传播的方式更新网络参数,得到初步的单通道融合图像;再次,在红外及可见光判别器中,使用深度可分离卷积分别对源图像与初步融合图像进行像素判别;最后,在损失函数的约束下,双判别器不断将更多的细节信息添加到融合图像中。实验结果表明,相比于传统的融合算法,该方法在信息熵、平均梯度、空间频率、标准差、结构相似性损失和峰值信噪比等评价指标上分别平均提高了1.63%、1.02%、3.54%、5.49%、1.05%、0.23%,在一定程度上提升了融合图像的质量,丰富了背景的细节信息。     

基于多尺度特征融合和注意力机制的医学图像分割网络

针对传统编解码结构的医学图像分割网络存在特征信息利用率低、泛化能力不足等问题,该文提出了一种结合编解码模式的多尺度语义感知注意力网络(multi-scale semantic perceptual attention network,MSPA-Net) 。首先,该网络在解码路径加入双路径多信息域注意力模块(dual-channel multi-information domain attention module,DMDA) ,提高特征信息的提取能力;其次,网络在级联处加入空洞卷积模块(dense atrous convolution module,DAC) ,扩大卷积感受野;最后,借鉴特征融合思想,设计了可调节多尺度特征融合模块 (adjustable multi-scale feature fusion,AMFF) 和双路自学习循环连接模块(dual self-learning recycle connection module,DCM) ,提升网络的泛化性和鲁棒性。为验证网络的有效性,在CVC-ClinicDB、ETIS-LaribPolypDB、COVID-19 CHEST X-RAY、Kaggle_3m、ISIC2017和Fluorescent Neuronal Cells等数据 集上进行验证,实验结果表明,相似系数分别达到了94.96%、92.40%、99.02%、90.55%、92.32%和75.32%。因此,新的分割网络展现了良好的泛化能力,总体性能优于现有网络,能够较好实现通用医学图像的有效分割。     

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.     

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.     

Underwater image super-resolution using multi-stage information distillation networks

Recently, single image super-resolution (SISR) has been widely applied in the fields of underwater robot vision and obtained remarkable performance. However, most current methods generally suffered from the problem of a heavy burden on computational resources with large model sizes, which limited their real-world underwater robotic applications. In this paper, we introduce and tackle the super resolution (SR) problem for underwater robot vision and provide an efficient solution for near real-time applications. We present a novel lightweight multi-stage information distillation network, named MSIDN, for better balancing performance against applicability, which aggregates the local distilled features from different stages for more powerful feature representation. Moreover, a novel recursive residual feature distillation (RRFD) module is constructed to progressively extract useful features with a modest number of parameters in each stage. We also propose a channel interaction & distillation (CI&D) module that employs channel split operation on the preceding features to produce two-part features and utilizes the inter channel-wise interaction information between them to generate the distilled features, which can effectively extract the useful information of current stage without extra parameters. Besides, we present USR-2K dataset, a collection of over 1.6K samples for large-scale underwater image SR training, and a testset with an additional 400 samples for benchmark evaluation. Extensive experiments on several standard benchmark datasets show that the proposed MSIDN can provide state-of-the-art or even better performance in both quantitative and qualitative measurements.     

Recursive residual atrous spatial pyramid pooling network for single image deraining

In recent years, removing rain streaks from a single image has been a significant issue for outdoor vision tasks. In this paper, we propose a novel recursive residual atrous spatial pyramid pooling network to directly recover the clear image from rain image. Specifically, we adopt residual atrous spatial pyramid pooling (ResASPP) module which is constructed by alternately cascading a ResASPP block with a residual block to exploit multi-scale rain information. Besides, taking the dependencies of deep features across stages into consideration, a recurrent layer is introduced into ResASPP to model multi-stage processing procedure from coarse to fine. For each stage in our recursive network we concatenate the stage-wise output with the original rainy image and then feed them into the next stage. Furthermore, the negative SSIM loss and perceptual loss are employed to train the proposed network. Extensive experiments on both synthetic and real-world rainy datasets demonstrate that the proposed method outperforms the state-of-the-art deraining methods.     

TDFSSD: Top-Down Feature Fusion Single Shot MultiBox Detector

Object detection across different scales is challenging as the variances of object scales. Thus, a novel detection network, Top-Down Feature Fusion Single Shot MultiBox Detector (TDFSSD), is proposed. The proposed network is based on Single Shot MultiBox Detector (SSD) using VGG-16 as backbone with a novel, simple yet efficient feature fusion module, namely, the Top-Down Feature Fusion Module. The proposed module fuses features from higher-level features, containing semantic information, to lower-level features, containing boundary information, iteratively. Extensive experiments have been conducted on PASCAL VOC2007, PASCAL VOC2012, and MS COCO datasets to demonstrate the efficiency of the proposed method. The proposed TDFSSD network is trained end to end and outperforms the state-of-the-art methods across the three datasets. The TDFSSD network achieves 81.7% and 80.1% mAPs on VOC2007 and 2012 respectively, which outperforms the reported best results of both one-stage and two-stage frameworks. In the meantime, it achieves 33.4% mAP on MS COCO test-dev, especially 17.2% average precision (AP) on small objects. Thus all the results show the efficiency of the proposed method on object detection. Code and model are available at: https://github.com/dongfengxijian/TDFSSD.     

Single image deblurring with cross-layer feature fusion and consecutive attention

Single image deblurring aims to restore the single blurry image to its sharp counterpart and remains an active topic of enduring interest. Recently, deep Convolutional Neural Network (CNN) based methods have achieved promising performance. However, two primary limitations mainly exist on those CNNs-based image deblurring methods: most of them simply focus on increasing the complexity of the network, and rarely make full use of features extracted by encoder. Meanwhile, most of the methods perform the deblurred image reconstruction immediately after the decoder, and the roles of the decoded features are always underestimated. To address these issues, we propose a single image deblurring method, in which two modules to fuse multiple features learned in encoder (the Cross-layer Feature Fusion (CFF) module) and manipulate the features after decoder (the Consecutive Attention Module (CAM)) are specially designed, respectively. The CFF module is to concatenate different layers of features from encoder to enhance rich structural information to decoder, and the CAM module is able to generate more important and correlated textures to the reconstructed sharp image. Besides, the ranking content loss is employed to further restore more realistic details in the deblurred images. Comprehensive experiments demonstrate that our proposed method can generate less blur and more textures in deblurred image on both synthetic datasets and real-world image examples.     

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.     

Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

融入残差注意力机制的DeepLabV3+图像拼接篡改取证网络

针对现有图像拼接检测网络模型存在边缘信息关注度不够、像素级精准定位效果不够好等问题,提出一种融入残差注意力机制的DeepLabV3+图像拼接篡改取证方法,该方法利用编-解码结构实现像素级图像的拼接篡改定位。在编码阶段,将高效注意力模块融入ResNet101的残差模块中,通过残差模块的堆叠以减小不重要的特征比重,凸显拼接篡改痕迹;其次,利用带有空洞卷积的空间金字塔池化模块进行多尺度特征提取,将得到的特征图进行拼接后通过空间和通道注意力机制进行语义信息建模。在解码阶段,通过融合多尺度的浅层和深层图像特征提升图像的拼接伪造区域的定位精度。实验结果表明,在CASIA 1.0、COLUMBIA和CARVALHO数据集上的拼接篡改定位精度分别达到了0.761、0.742和0.745,所提方法的图像拼接伪造区域定位性能优于一些现有的方法,同时该方法对JPEG压缩也具有更好的鲁棒性。