Image super-resolution is a challenging task and has attracted increasing attention in research and industrial communities. In this paper, we propose a novel end-to-end Attention-based DenseNet with Residual Deconvolution named as ADRD. In our ADRD, a weighted dense block, in which the current layer receives weighted features from all previous levels, is proposed to capture valuable features rely in dense layers adaptively. And a novel spatial attention module is presented to generate a group of attentive maps for emphasizing informative regions. In addition, we design an innovative strategy to upsample residual information via the deconvolution layer, so that the high-frequency details can be accurately upsampled. Extensive experiments conducted on publicly available datasets demonstrate the promising performance of the proposed ADRD against the state-of-the-arts, both quantitatively and qualitatively.
Beijing Normal University（北京师范大学）；Tianjin University（天津大学）；Sensetime Research（商汤科技研究院）
Image deblurring, a.k.a. image deconvolution, recovers a clear image from pixel superposition caused by blur degradation. Few deep convolutional neural networks (CNN) succeed in addressing this task. In this paper, we first demonstrate that the minimum-mean-square-error (MMSE) solution to image deblurring can be interestingly unfolded into a series of residual components. Based on this analysis, we propose a novel iterative residual deconvolution (IRD) algorithm. Further, IRD motivates us to take one step forward to design an explicable and effective CNN architecture for image deconvolution. S…
We introduce Invertible Dense Networks (i-DenseNets), a more parameter efficient alternative to Residual Flows. The method relies on an analysis of the Lipschitz continuity of the concatenation in DenseNets, where we enforce the invertibility of the network by satisfying the Lipschitz constraint. Additionally, we extend this method by proposing a learnable concatenation, which not only improves the model performance but also indicates the importance of the concatenated representation. We demonstrate the performance of i-DenseNets and Residual Flows on toy, MNIST, and CIFAR10 data. Both i-Dense…
We present a deep-learning based computing framework for fast-and-accurate CT (DL-FACT) testing of COVID-19. Our CT-based DL framework was developed to improve the testing speed and accuracy of COVID-19 (plus its variants) via a DL-based approach for CT image enhancement and classification. The image enhancement network is adapted from DDnet, short for DenseNet and Deconvolution based network. To demonstrate its speed and accuracy, we evaluated DL-FACT across several sources of COVID-19 CT images. Our results show that DL-FACT can significantly shorten the turnaround time from days to minutes …
Tianjin University（天津大学）；Hong Kong Polytechnic University（香港理工大学）；Harbin Institute of Technology（哈尔滨工业大学）；Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；University of California, Merced（加州大学默塞德分校）
Most existing non-blind restoration methods are based on the assumption that a precise degradation model is known. As the degradation process can only be partially known or inaccurately modeled, images may not be well restored. Rain streak removal and image deconvolution with inaccurate blur kernels are two representative examples of such tasks. For rain streak removal, although an input image can be decomposed into a scene layer and a rain streak layer, there exists no explicit formulation for modeling rain streaks and the composition with scene layer. For blind deconvolution, as estimation e…
Sichuan University（四川大学）；University of British Columbia（不列颠哥伦比亚大学）；Xidian University（西安电子科技大学）；Incheon National University（仁川大学）；Shandong University of Technology（山东理工大学）
In computer vision and image processing tasks, image fusion has evolved into an attractive research field. However, recent existing image fusion methods are mostly built on pixel-level operations, which may produce unacceptable artifacts and are time-consuming. In this paper, a symmetric encoder-decoder with a residual block (SEDR) for infrared and visible image fusion is proposed. For the training stage, the SEDR network is trained with a new dataset to obtain a fixed feature extractor. For the fusion stage, first, the trained model is utilized to extract the intermediate features and compens…
Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR)（德国航空航天中心遥感技术研究所（IMF））；Signal Processing in Earth Observation (SiPEO), Technical University of Munich (TUM)（慕尼黑工业大学地球观测信号处理研究所（SiPEO））
In this paper we tackle a very novel problem, namely height estimation from a single monocular remote sensing image, which is inherently ambiguous, and a technically ill-posed problem, with a large source of uncertainty coming from the overall scale. We propose a fully convolutional-deconvolutional network architecture being trained end-to-end, encompassing residual learning, to model the ambiguous mapping between monocular remote sensing images and height maps. Specifically, it is composed of two parts, i.e., convolutional sub-network and deconvolutional sub-network. The former corresponds to…
In blind image deconvolution, priors are often leveraged to constrain the solution space, so as to alleviate the under-determinacy. Priors which are trained separately from the task of deconvolution tend to be instable, or ineffective. We propose the Golf Optimizer, a novel but simple form of network that learns deep priors from data with better propagation behavior. Like playing golf, our method first estimates an aggressive propagation towards optimum using one network, and recurrently applies a residual CNN to learn the gradient of prior for delicate correction on restoration. Experiments s…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Deep fully convolutional neural network (FCN) based architectures have shown great potential in medical image segmentation. However, such architectures usually have millions of parameters and inadequate number of training samples leading to over-fitting and poor generalization. In this paper, we present a novel highly parameter and memory efficient FCN based architecture for medical image analysis. We propose a novel up-sampling path which incorporates long skip and short-cut connections to overcome the feature map explosion in FCN like architectures. In order to processes the input images at …
Sun Yat-sen University（中山大学）；The Hong Kong Polytechnic University（香港理工大学）；SenseTime Group Limited（商汤集团有限公司）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, Sun Yat-sen University（中山大学机器智能与先进计算教育部重点实验室）
Single image super resolution (SR), which refers to reconstruct a higher-resolution (HR) image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials. Despite the breakthroughs of recently proposed SR methods using convolutional neural networks (CNNs), their generated results usually lack of preserving structural (high-frequency) details. In this paper, regarding global boundary context and residual context as complimentary information for enhancing structural details in image restoration, we develop a contextualized multi-t…
Residual network (ResNet) and densely connected network (DenseNet) have significantly improved the training efficiency and performance of deep convolutional neural networks (DCNNs) mainly for object classification tasks. In this paper, we propose an efficient network architecture by considering advantages of both networks. The proposed method is integrated into an encoder-decoder DCNN model for medical image segmentation. Our method adds additional skip connections compared to ResNet but uses significantly fewer model parameters than DenseNet. We evaluate the proposed method on a public datase…
Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
Center for Advanced Systems Understanding (CASUS)（先进系统理解中心）；Helmholtz-Zentrum Dresden-Rossendorf e. V. (HZDR)（德累斯顿-罗斯托克研究所）；Max Delbrück Center for Molecular Medicine in the Helmholtz Association（马克斯·德尔布吕克分子医学研究中心）；Institute of Medical Physics and Biophysics, Charite-Universitätsmedizin（医学物理与生物物理研究所）；Institute of Computer Science, University of Wrocław（沃林福大学计算机科学研究所）
Deep learning based single image super-resolution methods use a large number of training datasets and have recently achieved great quality progress both quantitatively and qualitatively. Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual learning without exploring the feature abstraction and analysis. We propose a Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best…
Convolutional Neural Networks (CNN) increase depth by stacking convolutional layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolutional layers does not make the network train better, and skip connection (residual learning) can improve network model performance. For the image classification task, models with global densely connected architectures perform well in large datasets like ImageNet, but are not suitable for small datasets such as CIFAR-10 and SVHN. Different from dense connections, we propose two new algorithms to …
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual. Furthermore, SMG module is equipped with an efficient two-stage pipeline, which aims to DenseNet-like architectures that need to integrate all previous outputs, i.e., squeezing the incoming informative but redundant features gradually by hierarchical convolutions as a hourglass shape and then exciting it by multi-kernel depthwise convolutions, the output of which woul…
We introduce a new deep convolutional neural network, CrescendoNet, by stacking simple building blocks without residual connections. Each Crescendo block contains independent convolution paths with increased depths. The numbers of convolution layers and parameters are only increased linearly in Crescendo blocks. In experiments, CrescendoNet with only 15 layers outperforms almost all networks without residual connections on benchmark datasets, CIFAR10, CIFAR100, and SVHN. Given sufficient amount of data as in SVHN dataset, CrescendoNet with 15 layers and 4.1M parameters can match the performanc…
Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account. We investigate the generalized notion of frames designed with image properties in mind, as alternatives to this parametrization. We show that frame-based ResNets and Densenets can improve performance on Cifar-10+ consistently, while having additional pleasant properties like steerability. By exploiting these transformation properties explicitly, we arrive at dynamic steerable blocks. They are an extension of residual blocks, that are able to se…
AI-Driven Diabetic Retinopathy Diagnosis Enhancement through Image Processing and Salp Swarm Algorithm-Optimized Ensemble Network
Central South University（中南大学）；National University of Computer & Emerging Science（国家计算机与新兴科学大学）；German Research Center for Artificial Intelligence（德国人工智能研究中心）；Intelligentx GmbH（Intelligentx有限公司）；Rhineland-Palatinate Technical University of Kaiserslautern-Landau（莱茵兰-普法尔茨州 Kaiserslautern-Landau 工业大学）
A Deep Unrolling Model with Hybrid Optimization Structure for Hyperspectral Image Deconvolution
Department of Computer Engineering and Informatics, Patras University（计算机工程与信息学院，帕特拉大学）；Department Digital Media and Communication, Ionian University（数字媒体与通信系，伊奥尼亚大学）
National University of Singapore（新加坡国立大学）；Beijing Institute of Technology（北京理工大学）；National University of Defense Technology（国防科技大学）；Qihoo 360 AI Institute（奇虎360人工智能研究院）
In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally. By revealing the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, we find that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations. To enjoy the benefits from both path topologies, our proposed Dual Path Network shares common features while maintai…
In computer-aided diagnosis (CAD) focused on microscopy, denoising improves the quality of image analysis. In general, the accuracy of this process may depend both on the experience of the microscopist and on the equipment sensitivity and specificity. A medical image could be corrupted by both intrinsic noise, due to the device limitations, and, by extrinsic signal perturbations during image acquisition. Nowadays, CAD deep learning applications pre-process images with image denoising models to reinforce learning and prediction. In this work, an innovative and lightweight deep multiscale convol…
Institute of Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM), Université catholique de Louvain (UCL)（鲁汶天主教大学信息与通信技术、电子与应用数学研究所（ICTEAM））；Royal Observatory of Belgium（比利时皇家天文台）
Context: Characterization of instrumental effects in astronomical imaging is important in order to extract accurate physical information from the observations. The measured image in a real optical instrument is usually represented by the convolution of an ideal image with a Point Spread Function (PSF). Additionally, the image acquisition process is also contaminated by other sources of noise (read-out, photon-counting). The problem of estimating both the PSF and a denoised image is called blind deconvolution and is ill-posed. Aims: We propose a blind deconvolution scheme that relies on image r…
City University of Hong Kong（香港城市大学）；Singapore Telecommunications Limited（新加坡电信有限公司）；Nanyang Technological University（南洋理工大学）
Various architectures (such as GoogLeNets, ResNets, and DenseNets) have been proposed. However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters. To handle these challenging issues, we propose Micro-Dense Nets, a novel architecture with global residual learning and local micro-dense aggregations. Specifically, residual learning aims to efficiently retrieve features from different convolutional blocks, while the micro-dense aggregation is able to enhance each block and avoid redundancy of convolutional layers by lessen…
Coronavirus Disease 2019 (COVID-19) is caused by severe acute respiratory syndrome coronavirus 2 virus (SARS-CoV-2). The virus transmits rapidly; it has a basic reproductive number R of 2.2-2.7. In March 2020, the World Health Organization declared the COVID-19 outbreak a pandemic. COVID-19 is currently affecting more than 200 countries with 6M active cases. An effective testing strategy for COVID-19 is crucial to controlling the outbreak but the demand for testing surpasses the availability of test kits that use Reverse Transcription Polymerase Chain Reaction (RT-PCR). In this paper, we prese…
Hefei University of Technology（合肥工业大学）；Soochow University（苏州大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；South China Normal University（华南师范大学）；University of Science and Technology of China（中国科学技术大学）
Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Networks (DenseNet), have achieved great success for image representation by discovering deep hierarchical information. However, most existing networks simply stacks the convolutional layers and hence failing to fully discover local and global feature information among layers. In this paper, we mainly explore how to enhance the local and global dense feature flow by exploiting hierarchical features fully from all the convolution layers. Technically, we propose an efficient and effective CNN framework, i.e., Fast Dense Resid…
In visual recognition, the key to the performance improvement of ResNet is the success in establishing the stack of deep sequential convolutional layers using identical mapping by a shortcut connection. It results in multiple paths of data flow under a network and the paths are merged with the equal weights. However, it is questionable whether it is correct to use the fixed and predefined weights at the mapping units of all paths. In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. The weight val…
Recently, a lot of single stage detectors using multi-scale features have been actively proposed. They are much faster than two stage detectors that use region proposal networks (RPN) without much degradation in the detection performances. However, the feature maps in the lower layers close to the input which are responsible for detecting small objects in a single stage detector have a problem of insufficient representation power because they are too shallow. There is also a structural contradiction that the feature maps have to deliver low-level information to next layers as well as contain h…
The binary segmentation of roads in very high resolution (VHR) remote sensing images (RSIs) has always been a challenging task due to factors such as occlusions (caused by shadows, trees, buildings, etc.) and the intra-class variances of road surfaces. The wide use of convolutional neural networks (CNNs) has greatly improved the segmentation accuracy and made the task end-to-end trainable. However, there are still margins to improve in terms of the completeness and connectivity of the results. In this paper, we consider the specific context of road extraction and present a direction-aware resi…
Sichuan University（四川大学）；Chengdu University of Information Technology（成都信息工程大学）；Southeast University（东南大学）；West China Hospital of Sichuan University（四川大学华西医院）；Southern Medical University（南方医科大学）
Structure-preserved denoising of 3D magnetic resonance imaging (MRI) images is a critical step in medical image analysis. Over the past few years, many algorithms with impressive performances have been proposed. In this paper, inspired by the idea of deep learning, we introduce an MRI denoising method based on the residual encoder-decoder Wasserstein generative adversarial network (RED-WGAN). Specifically, to explore the structure similarity between neighboring slices, a 3D configuration is utilized as the basic processing unit. Residual autoencoders combined with deconvolution operations are …
Wuhan University of Technology（武汉理工大学）；Ningbo First Hospital（宁波市第一医院）；The First People’s Hospital of Tianmen（天门市第一人民医院）；Wuhan Institute of Physics and Mathematics, Chinese Academy of Sciences（中国科学院武汉物理与数学研究所）
In order to address the issue that medical image would suffer from severe blurring caused by the lack of high-frequency details in the process of image super-resolution reconstruction, a novel medical image super-resolution method based on dense neural network and blended attention mechanism is proposed. The proposed method adds blended attention blocks to dense neural network(DenseNet), so that the neural network can concentrate more attention to the regions and channels with sufficient high-frequency details. Batch normalization layers are removed to avoid loss of high-frequency texture deta…
Stanford University（斯坦福大学）；Varian Medical Systems（瓦里安医疗系统公司）；Huiyihuiying Medical Co（慧医慧影医疗公司）；Google Inc（谷歌公司）
Segmentation of livers and liver tumors is one of the most important steps in radiation therapy of hepatocellular carcinoma. The segmentation task is often done manually, making it tedious, labor intensive, and subject to intra-/inter- operator variations. While various algorithms for delineating organ-at-risks (OARs) and tumor targets have been proposed, automatic segmentation of livers and liver tumors remains intractable due to their low tissue contrast with respect to the surrounding organs and their deformable shape in CT images. The U-Net has gained increasing popularity recently for ima…
Scalable Residual Feature Aggregation Framework with Hybrid Metaheuristic Optimization for Robust Early Pancreatic Neoplasm Detection in Multimodal CT Imaging
An Improved ResNet50 Model for Predicting Pavement Condition Index (PCI) Directly from Pavement Images
TriQuint Semiconductor（TriQuint半导体公司）；XLIM Laboratory（XLIM实验室）；University of Limoges（利摩日大学）；Department of Electrical, Computer and Energy Engineering（电气、计算机与能源工程系）；University of Colorado（科罗拉多大学）；Qualcomm Inc.（高通公司）
United International University（联合国际大学）；Stamford University Bangladesh（孟加拉国斯坦福德大学）
Numerous diseases cause severe economic loss in the apple production-based industry. Early disease identification in apple leaves can help to stop the spread of infections and provide better productivity. Therefore, it is crucial to study the identification and classification of different apple foliar diseases. Various traditional machine learning and deep learning methods have addressed and investigated this issue. However, it is still challenging to classify these diseases because of their complex background, variation in the diseased spot in the images, and the presence of several symptoms …
