Adaptive Block Research Articles

A Generative Adversarial Network for infrared and visible image fusion using adaptive dense generator and Markovian discriminator

Existing infrared and visible image fusion algorithms have problems with reduced saliency for infrared targets and a lack of background texture information. To address this problem, a generative adversarial network for image fusion based on an attention mechanism is proposed in this study. This network consists of a generator, a discriminator, and an adaptive decision block. The generator employs a DenseNet-based cascade approach, which substantially lowers the information loss during the convolution process. A Markovian discriminator, unlike global discriminators, is embedded in the network. It divides images into patches, causing the network to focus on local regions and distinguishing the generated images as a whole. In addition, an adaptive decision block is included in the model to build an intensity dynamic mapping mechanism. To guide the computation for a certain content loss, a weighted map is created based on the intensity information of infrared images. Unlike the other loss functions, the weighted parameters of each component of the loss function are adaptively evaluated. To demonstrate the effectiveness of the proposed method, qualitative and quantitative experiments on TNO and RoadScene datasets are carried out. The experimental findings suggest that the proposed technique retains more significant characteristics in source images and produces fused images with rich texture details. Furthermore, the system noise resistance of each approach is examined. Under the condition of different noise, the fusion results of our approach still exhibit less distortion and a higher peak signal-to-noise ratio when compared to other state-of-the-art fusion methods.

Deep supervision feature refinement attention network for medical image segmentation

The improvement of medical technology is closely related to the development of computers. Deep learning methods have become an important means for medical image processing, and their accuracy in processing lesions will have a significant impact on the final diagnosis result. Currently, some traditional algorithms and classical deep learning methods are no longer able to meet the increasing demand for higher accuracy in medical image processing. In order to achieve better performance in handling the edge and detail features of lesions, we create the Deep Supervision Feature Refinement Attention Network (DSFRA-Net) through extensive experiments. In DSFRA-Net, the Depth Feature Attention Block is created to enhance the long-range dependency between pixels in deep neural networks. The Feature Refinement Block is developed to enhance the details in shallow features. The Adaptive Feature Extraction Block is created to strengthen the fusion of semantic information and detail information. A deep supervision mechanism is used to supervise each layer of the feature reconstruction process, feeding back the training in the form of a loss function to optimize the training. DSFRA-Net experiments on four datasets, all of which show better performance than the current mainstream networks. It shows superior capabilities in areas such as feature continuity and detailed feature processing.

MHAN: Multi-Stage Hybrid Attention Network for MRI reconstruction and super-resolution

High-quality magnetic resonance imaging (MRI) affords clear body tissue structure for reliable diagnosing. However, there is a principal problem of the trade-off between acquisition speed and image quality. Image reconstruction and super-resolution are crucial techniques to solve these problems. In the main field of MR image restoration, most researchers mainly focus on only one of these aspects, namely reconstruction or super-resolution. In this paper, we propose an efficient model called Multi-Stage Hybrid Attention Network (MHAN) that performs the multi-task of recovering high-resolution (HR) MR images from low-resolution (LR) under-sampled measurements. Our model is highlighted by three major modules: (i) an Amplified Spatial Attention Block (ASAB) capable of enhancing the differences in spatial information, (ii) a Self-Attention Block with a Data-Consistency Layer (DC-SAB), which can improve the accuracy of the extracted feature information, (iii) an Adaptive Local Residual Attention Block (ALRAB) that focuses on both spatial and channel information. MHAN employs an encoder–decoder architecture to deeply extract contextual information and a pipeline to provide spatial accuracy. Compared with the recent multi-task model T2Net, our MHAN improves by 2.759 dB in PSNR and 0.026 in SSIM with scaling factor ×2 and acceleration factor 4× on T2 modality.

Adaptive rate image compressive sensing based on the hybrid sparsity estimation model

In some actual image compressive sensing (CS) systems, the sparsity of the original image signals is unknown on the sampling side. Resources on the sampling side are also limited. Therefore, it is a challenging task to implement adaptive rate allocation on the sampling side of a CS system. In this paper, a novel adaptive rate allocation block CS scheme for images based on a hybrid sparsity estimation model is proposed. First, a cosine similarity sparsity estimation model is constructed by directly modeling the measurement results, and on the reconstruction side, a thresholding cosine transform sparsity estimation model is constructed according to the initial reconstructed image. Then, the sparsity estimates generated by the above two models are fused according to their respective characteristics using a Bayesian probability fusion algorithm. The advantage of the proposed scheme is that it can significantly improve the accuracy of the final sparsity estimates while limiting the computational complexity on the sampling side, which makes it exceptionally suitable for wireless sensor network applications. On the reconstruction side, we propose an energy-based adaptive global reconstruction model, that can further reduce block artifacts caused by block-based CS. The experiment results show that, compared with previous state-of-the-art schemes, the proposed scheme can achieve a significant improvement in the peak signal-to-noise ratio at the same sampling rate.

Bridging Multi-Scale Context-Aware Representation for Object Detection

Feature Pyramid Network (FPN) exploits multi-scale fusion representation to deal with scale variances in object detection. However, it ignores the context information gap across different levels. In this paper, we develop a plug-and-play detector, the multi-scale context-aware feature pyramid network to unleash the power of feature pyramid representation. Based on the dilated feature map at the highest level of the backbone, we propose the cross-scale context aggregation block to make full use of context information in the feature pyramid. Moreover, we extract discriminative features among different levels by the adaptive context aggregation block for robust object detection. Comprehensive experiments on MS-COCO demonstrate the effectiveness and efficiency of the proposed network, where about 1.0 ~ 3.0 AP improvements are achieved compared with existing FPN-based methods. In addition, we also conduct extensive experiments on pixel-level prediction tasks, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., instance segmentation, semantic segmentation, and panoptic segmentation, which further verify the effectiveness of the proposed method.

Mutual channel prior guided dual-domain interaction network for single image raindrop removal

Removing raindrops adhering to lenses or glass is challenging since raindrops have more complex internal structures and optical effects than rain streaks. Existing raindrop removal methods typically employ single-channel masks for raindrop representation. However, these methods ignore the complementarity of priors between different channels, thereby losing the color and transparency information of raindrops. Moreover, simply applying the same processing across different pixels is insufficient to deal with spatially-varying degradation. To address these limitation, we propose a novel Mutual channel prior guided Dual-domain Interaction Network (MDINet) for single image raindrop removal. Specifically, to effectively guide the restoration of the raindrop region, we propose a mutual channel prior by modeling the multi-channel raindrop soft mask, in which the enriched color and transparency information of raindrops are represented and learned by our model. To tackle the spatially-varying degradation, we design the dual-domain interaction block to capture global low-frequency content and local high-frequency details. Simultaneously, a spatially adaptive modulation block is devised to handle complicated and diverse raindrops. Moreover, we propose a contrastive discrimination strategy to motivate the restored image to approach the clean image and stay away from the raindrop image in the representation space. Extensive experiments on benchmark datasets and real-world images indicate that the proposed method achieves qualitative and quantitative superiority against state-of-the-art methods.

Exemplar-Guided Sedimentary Facies Modeling for Bridging Pattern Controllability Gap

Inferring subsurface structure from sparse log data is crucial for geology. Recently, deep-learning-based methods, which provide sufficient prior knowledge from training sets, have been proven to aid in sedimentary facies modeling. However, these methods suffer from suboptimal controllability of the geological model, i.e., the expected geological pattern fails to be specified, resulting in unpredictable generated geological structures. To bridge the gap, we propose a novel Exemplar-Guided Facies Modeling (EGFM) approach, which synthesizes a facies model from log data given a pattern exemplar. The key insight in EGFM is to decouple the content and pattern in the target model, where the content refers to the match with well data, and the pattern is the properties of geological structures, such as fluvial course and shape. On the basis of well data as the hard condition, a pattern exemplar is introduced as the reference model for geological realizations. In addition to preserving the commonalities of the holistic geological pattern (from the geological image set), such as structural connectivity, the pattern details of the geological realization can be tuned through pattern exemplars. Moreover, we introduce an adaptive feature fusion block (AFB) to adaptively fuse the content and pattern features for more natural results. Extensive experimental results on two river data sets demonstrate that our proposed EGFM for conditional facies modeling achieves satisfying visual quality and pattern controllability.

Fuzzy Rule Based Adaptive Block Compressive Sensing for WSN Application

Transmission of high volume of data in a restricted wireless sensor network (WSN) has come up as a challenge due to high-energy consumption and larger bandwidth requirement. To address the issues of high-energy consumption and efficient data transmission adaptive block compressive sensing (ABCS) is one of the optimum solution. ABCS framework is well capable to adapt the sampling rate depending on the block’s features information that offers higher sampling rate for less compressible blocks and lower sampling rate for more compressible blocks In this paper, we have proposed a novel fuzzy rule based adaptive compressive sensing approach by leveraging the saliency and the edge features of the image making the sampling rate selection completely automatic. Adaptivity of the block sampling ratio has been decided based on the fuzzy logic system (FLS) by considering two important features i.e., edge and saliency information. The proposed framework is experimented on standard dataset, Kodak data set, CCTV images and the Set5 data set images. It achieved an average PSNR of 34.26 and 33.2 and an average SSIM of 0.87 and 0.865 for standard images and CCTV images respectively. Again for high resolution Kodak data set and Set 5 dataset images, it achieved an average PSNR of 32.95 and 31.72 and SSIM of 0.832 and 0.8 respectively. The experiments and the result analysis show that proposed method is efficacious than the state of the art methods in both subjective and objective evaluation metrics.

Depth map continuous super-resolution with local implicit guidance function

Depth super-resolution (SR) is an effective approach to compensate the resolution gap between the relative low resolution of current depth sensing devices and the increasing demands of high-resolution content in many nowadays applications and future scenarios. However, most convolutional neural networks (CNNs) for depth SR are designed for particular integer SR ratios ( e.g., 2×, 4×, or 8×) or their combinations, which limits its practical applications that usually demands fractional SR ratios. This paper proposes a depth map continuous SR (DCSR) framework that is able to achieve resolution adaptation at arbitrary SR ratios. Specifically, we proposed an encoder with a dual-stream architecture. Using depth map and the guided color image as input, each stream interacts with the other by a series of adaptive resize blocks (ARBs) to retain essential details and resize stabilization across features of various resolutions. In the decoder, depth information at arbitrary missing locations is fitted as the weighted prediction of neural implicit functions (NIFs) from latent codes containing relative coordinate, target pixel size, and fused depth-color features. Extensive experiments demonstrate that the proposed DCSR method provides high quality depth SR results at arbitrary ratios, which is a promising merit for practical applications. Code will be released upon the publication of this work.

A visually secure image encryption scheme based on adaptive block compressed sensing and non-negative matrix factorization

The traditional block compressive sensing theory cannot make full use of the difference of image block information characteristics for sampling, and the measurement matrix cannot fully measure the image according to the image block information characteristics. To solve these problems, we design an adaptive block compressed sensing (ABCS) algorithm, and we propose a visually secure image encryption scheme based on ABCS and non-negative matrix factorization (NMF). First, the plain image is decomposed by Tetrolet transform. Then, we perform matrix shuffling to optimize the sparsity of the sparse matrix. Next, adaptive sampling and measurement are performed according to the information distribution characteristics between the image blocks to compress the image to a quarter of its original size. Last, we design a scrambling–diffusion framework based on tetrominoes to obtain the secret image, which is then embedded into the carrier image by means of NMF to obtain a visually secure cipher image. The experimental results show that the proposed scheme can consider the security of image information transmission and the integrity of reception, and has good resistance to various attacks.

Dual-aware transformer network for single-image super-resolution

The advent of deep learning has enabled image super-resolution (SR) technology to achieve tremendous success. The recent exploration between convolutional neural network (CNN) and transformer has produced an impressive performance. However, the huge model size and heavy computational cost occupied by most approaches cannot be ignored. Additionally, the global and local modeling of image features is not well utilized and explored, which is important for texture content reconstruction. In this study, we present an efficient and lightweight network based on CNN and transformer for image SR, dubbed dual-aware transformer network (DATN). Specifically, a dual-aware fusion module (DAFM), consisting of spatial-aware adaptive block (SAAB) and global-aware fusion block (GAFB), learns local and global features in a complementary manner for yielding abundant content details. SAAB delivers the captured spatial information to GAFB in parallel, whereas GAFB establishes long-range spatial dependencies among diverse features to boost the network’s ability for recovering texture details. Further, in the upsampling stage, our proposed transformer-empowered upsampling module aggregates global information from the transformer module to generate location-wise reassembly kernels for content-aware upsampling. In such way, feature-rich information is highlighted adaptively to reconstruct high-quality images with maximum efficiency. Experimental results reveal that our proposed DATN achieves high qualitative performance while maintaining low computational demands, surpassing most state-of-the-art SR networks.

Interference Suppression in EEG Dipole Source Localization through Reduced-Rank Beamforming

In this paper, we propose new neural activity indices for the solution of the inverse problem of localizing sources of cortical activity from electroencephalography (EEG) measurements. Such indices are based on reduced-rank beamformers, specifically the generalized sidelobe canceler (GSC), and with the purpose of suppressing the contribution of interfering sources and noise. Here, the GSC is modified with an adaptive blocking matrix (ABM) to optimally estimate and later suppress unwanted brain sources. With respect to the rank-reduction, this is achieved through the cross-spectral metrics (CSM) as they give a sense of the affinity of the beamformers’ eigenstructure to the orthogonal subspace of noise an interference. Based on that, two different neural indices are proposed for the assessment of brain activation. Our realistic simulations show that a more consistent source localization is achieved through the proposed indices in comparison to the use of the traditional full-rank approach, specifically for brain sources embedded in high background activity that originates at the brain cortex and thalamus. We also prove the applicability of our methods on the localization of sources on the visual cortex produced by steady-state visual-evoked potentials.

ACTION: Adaptive Cache Block Migration in Distributed Cache Architectures

Chip multiprocessors (CMP) with more cores have more traffic to the last-level cache (LLC) . Without a corresponding increase in LLC bandwidth, such traffic cannot be sustained, resulting in performance degradation. Previous research focused on data placement techniques to improve access latency in Non-Uniform Cache Architectures (NUCA) . Placing data closer to the referring core reduces traffic in cache interconnect. However, earlier data placement work did not account for the frequency with which specific memory references are accessed. The difficulty of tracking access frequency for all memory references is one of the main reasons why it was not considered in NUCA data placement. In this research, we present a hardware-assisted solution called ACTION ( A daptive C ache Block Migra tion ) to track the access frequency of individual memory references and prioritize placement of frequently referred data closer to the affine core. ACTION mechanism implements cache block migration when there is a detectable change in access frequencies due to a shift in the program phase. ACTION counts access references in the LLC stream using a simple and approximate method and uses a straightforward placement and migration solution to keep the hardware overhead low. We evaluate ACTION on a 4-core CMP with a 5x5 mesh LLC network implementing a partitioned D-NUCA against workloads exhibiting distinct asymmetry in cache block access frequency. Our simulation results indicate that ACTION can improve CMP performance by up to 7.5% over state-of-the-art (SOTA) D-NUCA solutions.

Dual parallel net: A novel deep learning model for rectal tumor segmentation via CNN and transformer with Gaussian Mixture prior

Segmentation of rectal cancerous regions from Magnetic Resonance (MR) images can help doctor define the extent of the rectal cancer and judge the severity of rectal cancer, so rectal tumor segmentation is crucial to improve the accuracy of rectal cancer diagnosis. However, accurate segmentation of rectal cancerous regions remains a challenging task due to the shape of rectal tumor has significant variations and the tumor and surrounding tissue are indistinguishable. In addition, in the early research on rectal tumor segmentation, most deep learning methods were based on convolutional neural networks (CNNs), and traditional CNN have small receptive field, which can only capture local information while ignoring the global information of the image. Nevertheless, the global information plays a crucial role in rectal tumor segmentation, so traditional CNN-based methods usually cannot achieve satisfactory segmentation results. In this paper, we propose an encoder-decoder network named Dual Parallel Net (DuPNet), which fuses transformer and classical CNN for capturing both global and local information. Meanwhile, as for capture features at different scales as well as to avoid accuracy loss and parameters reduction, we design a feature adaptive block (FAB) in skip connection between encoder and decoder. Furthermore, in order to utilize the apriori information of rectal tumor shape effectively, we design a Gaussian Mixture prior and embed it in self-attention mechanism of the transformer, leading to robust feature representation and accurate segmentation results. We have performed extensive ablation experiments to verify the effectiveness of our proposed dual parallel encoder, FAB and Gaussian Mixture prior on the dataset from the Shanxi Cancer Hospital. In the experimental comparison with the state-of-the-art methods, our method achieved a Mean Intersection over Union (MIoU) of 89.34% on the test set. In addition to that, we evaluated the generalizability of our method on the dataset from Xinhua Hospital, the promising results verify the superiority of our method.

Image Denoising Method Based on Harmonic Filtering and Non-Subsample Shear Wave Block Matching in Wavelength Domain

&lt;p&gt;Efficient noise filtering is the difficulty of image denoising on the premise of preserving the edge and internal texture information of the image. Therefore, this paper focused on adaptive Gaussian variational model and block matching image denoising method in the wave domain from the non-local point of view. At first, a 3D block match harmonic filtering model was establish in that wavelet domain, 3D transform was use to represent that real signals in the match block group in a sparse form, then the shrinkage threshold was used to achieve the purpose of pre-denoising, and the wavelet transform was then used to extract the high frequency part of the predictor image for filtering. In order to avoid edge blurring, Laplace-Gaussian algorithm was used to construct a new operator into the diffusion model, and the wavelet coefficients were reconstructed to obtain the final approximation of the original image. Secondly, a block matching denoising model based on shear wave was proposed. In order to avoid ill-conditioned problem, The multi-scale geometric analysis method using shearlet transform can improve the edge protection ability, and a block matching denoising model based on shearlet is proposed. The new model predicts the scaling threshold according to the statistical characteristics of the histogram, performs hard threshold filtering on the high-frequency sub-band to obtain the processed sub-band coefficients, and performs block matching 3D filtering on the decomposed low-frequency sub-band coefficients to obtain the processed coefficients. All processed subband coefficients are inversely transformed and reconstructed to obtain a denoised image. The analysis and simulation results showed that the two new models can effectively suppress noise and improve the clarity, and the block matching denoising based on shear wave had more advantages.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;

Adaptive Compressed Sampling Based on EMD for Wireless Sensor Networks

Image acquisition and communication in wireless sensor networks (WSNs) are key issues for some applications that require image sensing. Lowering the sampling rate and reducing the amount of data to be transmitted can greatly save hardware costs and power consumption to overcome communication bottlenecks. To serve this purpose, block compressed sampling (CS) can be used. For block CS, the sparsity of the signal to be sampled is an important parameter. On the sampling side of sensor nodes, we cannot obtain the complete digital signal. Therefore, it is challenging to perform adaptive rate sampling for block CS. In this article, a novel rate adaptive allocation block CS scheme based on empirical mode decomposition (EMD) is proposed. First, we calculate an energy matrix of measurement results (EMMR) and perform EMD on EMMR. Considering the high computational complexity of 2-D EMD, which will increase the burden on the sampling side, we propose a 1-D EMD based on zigzag scanning to decompose EMMR. Then, we can obtain an energy distribution map (EDM) of high-frequency components of EMMR. Finally, the adaptive allocation of sampling rate is carried out according to the EDM of high-frequency components. On the reconstruction side of WSN, we propose a reconstruction algorithm based on residual measurement results, which can further improve the reconstruction accuracy of images. The experiment results show that the proposed scheme has improved the accuracy in general compared with the previous schemes, and the subjective quality of the reconstructed images is also improved.

Classification of Brain Disorders in rs-fMRI via Local-to-Global Graph Neural Networks.

Recently, functional brain network has been used for the classification of brain disorders, such as Autism Spectrum Disorder (ASD) and Alzheimer's disease (AD). Existing methods either ignore the non-imaging information associated with the subjects and the relationship between the subjects, or cannot identify and analyze disease-related local brain regions and biomarkers, leading to inaccurate classification results. This paper proposes a local-to-global graph neural network (LG-GNN) to address this issue. A local ROI-GNN is designed to learn feature embeddings of local brain regions and identify biomarkers, and a global Subject-GNN is then established to learn the relationship between the subjects with the embeddings generated by the local ROI-GNN and the non-imaging information. The local ROI-GNN contains a self-attention based pooling module to preserve the embeddings most important for the classification. The global Subject-GNN contains an adaptive weight aggregation block to generate the multi-scale feature embedding corresponding to each subject. The proposed LG-GNN is thoroughly validated using two public datasets for ASD and AD classification. The experimental results demonstrated that it achieves the state-of-the-art performance in terms of various evaluation metrics.

Edge Detection Guide Network for Semantic Segmentation of Remote-Sensing Images

The acquisition of high-resolution satellite and airborne remote sensing images has been significantly simplified due to the rapid development of sensor technology. Several practical applications of high-resolution remote sensing images (HRRSIs) are based on semantic segmentation. However, single-modal HRRSIs are difficult to classify accurately in the complex situation of some scene objects; therefore, the semantic segmentation of multi-source information fusion is gaining popularity. The inherent difference between multimodal features and the semantic gap between multi-level features typically affect the performance of existing multi-mode fusion methods. We propose a multimodal fusion network based on edge detection to address these issues. This method aids multimodal information fusion by utilizing spatial information contained in the boundary. An edge detection guide module is included in the feature extraction stage to realize the boundary information through the fusion of details and semantics between high-level and low-level features. The boundary information is extended into the well-designed multimodal adaptive fusion block (MAFB) to obtain the multimodal fusion features. Furthermore, a residual adaptive fusion block (RAFB) and a spatial position module (SPM) in the feature decoding stage have been designed to fuse multi-level features from the standpoint of local and global dependence. We compared our method to several state-of-the-art (SOTA) methods using the International Society for Photogrammetry and Remote Sensing’s (ISPRS) Vaihingen and Potsdam datasets. The final results demonstrate that our method achieves excellent performance.

Atrial fibrillation medical image encryption algorithm based on deep learning and adaptive block

Atrial fibrillation medical image encryption algorithm based on deep learning and adaptive block

Atrial fibrillation medical image encryption algorithm based on deep learning and adaptive block

Atrial fibrillation medical image encryption algorithm based on deep learning and adaptive block