Reconstruction Module Research Articles

Multi-Scale Image- and Feature-Level Alignment for Cross-Resolution Person Re-Identification

Cross-Resolution Person Re-Identification (re-ID) aims to match images with disparate resolutions arising from variations in camera hardware and shooting distances. Most conventional works utilize Super-Resolution (SR) models to recover Low Resolution (LR) images to High Resolution (HR) images. However, because the SR models cannot completely compensate for the missing information in the LR images, there is still a large gap between the HR image recovered from the LR images and the real HR images. To tackle this challenge, we propose a novel Multi-Scale Image- and Feature-Level Alignment (MSIFLA) framework to align the images on multiple resolution scales at both the image and feature level. Specifically, (i) we design a Cascaded Multi-Scale Resolution Reconstruction (CMSR2) module, which is composed of three cascaded Image Reconstruction (IR) networks, and can continuously reconstruct multiple variables of different resolution scales from low to high for each image, regardless of image resolution. The reconstructed images with specific resolution scales are of similar distribution; therefore, the images are aligned on multiple resolution scales at the image level. (ii) We propose a Multi-Resolution Representation Learning (MR2L) module which consists of three-person re-ID networks to encourage the IR models to preserve the ID-discriminative information during training separately. Each re-ID network focuses on mining discriminative information from a specific scale without the disturbance from various resolutions. By matching the extracted features on three resolution scales, the images with different resolutions are also aligned at the feature-level. We conduct extensive experiments on multiple public cross-resolution person re-ID datasets to demonstrate the superiority of the proposed method. In addition, the generalization of MSIFLA in handling cross-resolution retrieval tasks is verified on the UAV vehicle dataset.

Individual age determination based on computed tomography knee analysis using artificial neural networks and computer vision: Preliminary results

BACKGROUND: Currently, studies have focused on the modernization of existing methods of forensic age assessment (bone and skeletal) through the active use of modern methods of medical imaging (e.g., computed tomography) and artificial intelligence for their analysis. This approach enables the creation of new methods for assessing biological age, which is characterized by increased accuracy and reproducibility.
 AIM: To develop and test an algorithm for predicting the biological age of an individual based on computed tomography analysis of the knee joint using artificial neural networks and computer vision.
 MATERIALS AND METHODS: This observational retrospective transverse (one time) study analyzed computed tomography scans (334) of the knee joint performed in the Departments of Radiation Diagnostics of the Priorov Central Institute for Trauma and Orthopedics, Vreden National Medical Center for Traumatology and Orthopedics, between 2018 and 2021. The study enrolled persons of both sexes aged 13–45 years. Cases of developmental abnormalities, knee injuries, signs of general connective tissue pathology were excluded. Research methods include the use of intelligent information technologies (a formalized set of mathematical and software solutions).
 RESULTS: Based on the experiments conducted, an algorithm for assessing age according to the computed tomography scans of the knee joint has been developed. The main components of the developed system are as follows: a preprocessing module, an intelligent computing core, a data analysis module, a three-dimensional reconstruction module, a property extraction module, and a final age assessment module. The essence of the proposed method is the simultaneous use of artificial neural networks and clearly formalized mathematical procedures for calculating the properties of the epiphyseal line. To obtain the results and conduct primary experimental studies that confirmed the feasibility, correctness, and operability of the method, software using the YOLOv5 neural network was developed. The result of the error matrix analysis after training shows a probability of correct recognition of the order of 80%. Verification of experimental studies was performed on 46 cases. At present, the age estimation error is approximately 1 year for children and adolescents.
 CONCLUSIONS: The experimental results have confirmed the adequacy of the age estimates obtained to the actual age of the individual and, consequently, the applicability of the proposed method in forensic medical institutions. The proposed method is currently implemented as a set of software components with subsequent manual integration of automatically calculated data. The plan was to supplement the database of computed tomography images to increase the training sample and the accuracy of age prediction.

Addiction-related brain networks identification via Graph Diffusion Reconstruction Network

Functional magnetic resonance imaging (fMRI) provides insights into complex patterns of brain functional changes, making it a valuable tool for exploring addiction-related brain connectivity. However, effectively extracting addiction-related brain connectivity from fMRI data remains challenging due to the intricate and non-linear nature of brain connections. Therefore, this paper proposed the Graph Diffusion Reconstruction Network (GDRN), a novel framework designed to capture addiction-related brain connectivity from fMRI data acquired from addicted rats. The proposed GDRN incorporates a diffusion reconstruction module that effectively maintains the unity of data distribution by reconstructing the training samples, thereby enhancing the model’s ability to reconstruct nicotine addiction-related brain networks. Experimental evaluations conducted on a nicotine addiction rat dataset demonstrate that the proposed GDRN effectively explores nicotine addiction-related brain connectivity. The findings suggest that the GDRN holds promise for uncovering and understanding the complex neural mechanisms underlying addiction using fMRI data.

Deep convolutional dictionary learning network for sparse view CT reconstruction with a group sparse prior

Purpose Numerous techniques based on deep learning have been utilized in sparse view computed tomography (CT) imaging. Nevertheless, the majority of techniques are instinctively constructed utilizing state-of-the-art opaque convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields and neglect nonlocal self-similarity prior information. Obtaining diagnostically valuable images from sparsely sampled projections is a challenging and ill-posed task.Method To address this issue, we propose a unique and understandable model named DCDL-GS for sparse view CT imaging. This model relies on a network comprised of convolutional dictionary learning and a nonlocal group sparse prior. To enhance the quality of image reconstruction, we utilize a neural network in conjunction with a statistical iterative reconstruction framework and perform a set number of iterations. Inspired by group sparsity priors, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Furthermore, our DCDL-GS model incorporates filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight and interpretable convolutional dictionary learning network to enhance the applicability of the model.Results The efficiency of our proposed DCDL-GS model in preserving edges and recovering features is demonstrated by the visual results obtained on the LDCT-P and UIH datasets. Compared to the results of the most advanced techniques, the quantitative results are enhanced, with increases of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse prior.Conclusion In this paper, we create a consolidated and enhanced mathematical model by integrating projection data and prior knowledge of images into a deep iterative model. The model is more practical and interpretable than existing approaches. The results from the experiment show that the proposed model performs well in comparison to the others.

AISOA-SSformer: An Effective Image Segmentation Method for Rice Leaf Disease Based on the Transformer Architecture.

Rice leaf diseases have an important impact on modern farming, threatening crop health and yield. Accurate semantic segmentation techniques are crucial for segmenting diseased leaf parts and assisting farmers in disease identification. However, the diversity of rice growing environments and the complexity of leaf diseases pose challenges. To address these issues, this study introduces an innovative semantic segmentation algorithm for rice leaf pests and diseases based on the Transformer architecture AISOA-SSformer. First, it features the sparse global-update perceptron for real-time parameter updating, enhancing model stability and accuracy in learning irregular leaf features. Second, the salient feature attention mechanism is introduced to separate and reorganize features using the spatial reconstruction module (SRM) and channel reconstruction module (CRM), focusing on salient feature extraction and reducing background interference. Additionally, the annealing-integrated sparrow optimization algorithm fine-tunes the sparrow algorithm, gradually reducing the stochastic search amplitude to minimize loss. This enhances the model's adaptability and robustness, particularly against fuzzy edge features. The experimental results show that AISOA-SSformer achieves an 83.1% MIoU, an 80.3% Dice coefficient, and a 76.5% recall on a homemade dataset, with a model size of only 14.71 million parameters. Compared with other popular algorithms, it demonstrates greater accuracy in rice leaf disease segmentation. This method effectively improves segmentation, providing valuable insights for modern plantation management. The data and code used in this study will be open sourced at https://github.com/ZhouGuoXiong/Rice-Leaf-Disease-Segmentation-Dataset-Code.

Source-Guided Target Feature Reconstruction for Cross-Domain Classification and Detection.

Existing cross-domain classification and detection methods usually apply a consistency constraint between the target sample and its self-augmentation for unsupervised learning without considering the essential source knowledge. In this paper, we propose a Source-guided Target Feature Reconstruction (STFR) module for cross-domain visual tasks, which applies source visual words to reconstruct the target features. Since the reconstructed target features contain the source knowledge, they can be treated as a bridge to connect the source and target domains. Therefore, using them for consistency learning can enhance the target representation and reduce the domain bias. Technically, source visual words are selected and updated according to the source feature distribution, and applied to reconstruct the given target feature via a weighted combination strategy. After that, consistency constraints are built between the reconstructed and original target features for domain alignment. Furthermore, STFR is connected with the optimal transportation algorithm theoretically, which explains the rationality of the proposed module. Extensive experiments on nine benchmarks and two cross-domain visual tasks prove the effectiveness of the proposed STFR module, e.g., 1) cross-domain image classification: obtaining average accuracy of 91.0%, 73.9%, and 87.4% on Office-31, Office-Home, and VisDA-2017, respectively; 2) cross-domain object detection: obtaining mAP of 44.50% on Cityscapes → Foggy Cityscapes, AP on car of 78.10% on Cityscapes → KITTI, MR -2 of 8.63%, 12.27%, 22.10%, and 40.58% on COCOPersons → Caltech, CityPersons → Caltech, COCOPersons → CityPersons, and Caltech → CityPersons, respectively.

Image Intrinsic-Based Unsupervised Monocular Depth Estimation in Endoscopy.

Unsupervised monocular depth estimation plays a vital role for endoscopy-based minimally invasive surgery (MIS). However, it remains challenging due to the distinctive imaging characteristics of endoscopy which disrupt the assumption of photometric consistency, a foundation relied upon by conventional methods. Distinct from recent approaches taking image pre-processing strategy, this paper introduces a pioneering solution through intrinsic image decomposition (IID) theory. Specifically, we propose a novel end-to-end intrinsic-based unsupervised monocular depth learning framework that is comprised of an image intrinsic decomposition module and a synthesis reconstruction module. This framework seamlessly integrates IID with unsupervised monocular depth estimation, and dedicated losses are meticulously designed to offer robust supervision for network training based on this novel integration. Noteworthy, we rely on the favorable property of the resulting albedo map of IID to circumvent the challenging images characteristics instead of pre-processing the input frames. The proposed method is extensively validated on SCARED and Hamlyn datasets, and better results are obtained than state-of-the-art techniques. Beside, its generalization ability and the effectiveness of the proposed components are also validated. This innovative method has the potential to elevate the quality of 3D reconstruction in monocular endoscopy, thereby enhancing the accuracy and robustness of augmented reality navigation technology in MIS. Our code will be available at: https://github.com/bobo909/IID-SfmLearner.

SRNet-YOLO: A model for detecting tiny and very tiny pests in cotton fields based on super-resolution reconstruction.

Effective pest management is important during the natural growth phases of cotton in the wild. As cotton fields are infested with "tiny pests" (smaller than 32×32 pixels) and "very tiny pests" (smaller than 16×16 pixels) during growth, making it difficult for common object detection models to accurately detect and fail to make sound agricultural decisions. In this study, we proposed a framework for detecting "tiny pests" and "very tiny pests" in wild cotton fields, named SRNet-YOLO. SRNet-YOLO includes a YOLOv8 feature extraction module, a feature map super-resolution reconstruction module (FM-SR), and a fusion mechanism based on BiFormer attention (BiFormerAF). Specially, the FM-SR module is designed for the feature map level to recover the important feature in detail, in other words, this module reconstructs the P5 layer feature map into the size of the P3 layer. And then we designed the BiFormerAF module to fuse this reconstruct layer with the P3 layer, which greatly improves the detection performance. The purpose of the BiFormerAF module is to solve the problem of possible loss of feature after reconstruction. Additionally, to validate the performance of our method for "tiny pests" and "very tiny pests" detection in cotton fields, we have developed a large dataset, named Cotton-Yellow-Sticky-2023, which collected pests by yellow sticky traps. Through comprehensive experimental verification, we demonstrate that our proposed framework achieves exceptional performance. Our method achieved 78.2% mAP on the "tiny pests" test result, it surpasses the performance of leading detection models such as YOLOv3, YOLOv5, YOLOv7 and YOLOv8 by 6.9%, 7.2%, 5.7% and 4.1%, respectively. Meanwhile, our results on "very tiny pests" reached 57% mAP, which are 32.2% higher than YOLOv8. To verify the generalizability of the model, our experiments on Yellow Sticky Traps (low-resolution) dataset still maintained the highest 92.8% mAP. The above experimental results indicate that our model not only provides help in solving the problem of tiny pests in cotton fields, but also has good generalizability and can be used for the detection of tiny pests in other crops.

Multispectral Image Stitching via Global-Aware Quadrature Pyramid Regression.

Image stitching is a critical task in panorama perception that involves combining images captured from different viewing positions to reconstruct a wider field-of-view (FOV) image. Existing visible image stitching methods suffer from performance drops under severe conditions since environmental factors can easily impair visible images. In contrast, infrared images possess greater penetrating ability and are less affected by environmental factors. Therefore, we propose an infrared and visible image-based multispectral image stitching method to achieve all-weather, broad FOV scene perception. Specifically, based on two pairs of infrared and visible images, we employ the salient structural information from the infrared images and the textual details from the visible images to infer the correspondences within different modality-specific features. For this purpose, a multiscale progressive mechanism coupled with quadrature correlation is exploited to improve regression in different modalities. Exploiting the complementary properties, accurate and credible homography can be obtained by integrating the deformation parameters of the two modalities to compensate for the missing modality-specific information. A global-aware guided reconstruction module is established to generate an informative and broad scene, wherein the attentive features of different viewpoints are introduced to fuse the source images with a more seamless and comprehensive appearance. We construct a high-quality infrared and visible stitching dataset for evaluation, including real-world and synthetic sets. The qualitative and quantitative results demonstrate that the proposed method outperforms the intuitive cascaded fusion-stitching procedure, achieving more robust and credible panorama generation. Code and dataset are available at https://github.com/Jzy2017/MSGA.

Spatial Structure Constraints for Weakly Supervised Semantic Segmentation.

The image-level label has prevailed in weakly supervised semantic segmentation tasks due to its easy availability. Since image-level labels can only indicate the existence or absence of specific categories of objects, visualization-based techniques have been widely adopted to provide object location clues. Considering class activation maps (CAMs) can only locate the most discriminative part of objects, recent approaches usually adopt an expansion strategy to enlarge the activation area for more integral object localization. However, without proper constraints, the expanded activation will easily intrude into the background region. In this paper, we propose spatial structure constraints (SSC) for weakly supervised semantic segmentation to alleviate the unwanted object over-activation of attention expansion. Specifically, we propose a CAM-driven reconstruction module to directly reconstruct the input image from deep CAM features, which constrains the diffusion of last-layer object attention by preserving the coarse spatial structure of the image content. Moreover, we propose an activation self-modulation module to refine CAMs with finer spatial structure details by enhancing regional consistency. Without external saliency models to provide background clues, our approach achieves 72.7% and 47.0% mIoU on the PASCAL VOC 2012 and COCO datasets, respectively, demonstrating the superiority of our proposed approach. The source codes and models have been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/SSC.

Skip Connection Aggregation Transformer for Occluded Person Reidentification

The occlusion problem is a significant challenge for person re-identification. Recently, transformer-based methods have been introduced to solve the occlusion problem and achieve performance improvements. However, the existing methods only apply the features of the last transformer layer and fail to consider the alignment of visible body parts. They also ignore fine-grained local features. Thus they usually suffer from misalignment in occluded image matching. We observe that features from the high layers of the transformer focus on classification information and global features, while those from the middle layers pay more attention to pedestrians. We think that making full use of the features of different layers will facilitate alignment and then will promote re-identification accuracy. Therefore, we propose a novel skip connection aggregation transformer (SCAT) network by utilizing features from different transformer layers to increase the diversity of features and align visible body parts in occluded images. The diverse features include (1) features of the middle layer, which focus on the pedestrian in nonoccluded regions and favor alignment, (2) features of high layers, which focus on global information, (3) fine-grained local features, which are obtained by the part pooling encoder and the fusion reconstruction module. The part pooling encoder and the fusion reconstruction module are proposed to obtain part-based local features and fused local features, respectively. The experimental results on the occluded, partial, and holistic benchmarks demonstrate that our method can significantly promote the accuracy of occluded person re-identification.

Explicitly-Decoupled Text Transfer With Minimized Background Reconstruction for Scene Text Editing.

Scene text editing aims to replace the source text with the target text while preserving the original background. Its practical applications span various domains, such as data generation and privacy protection, highlighting its increasing importance in recent years. In this study, we propose a novel Scene Text Editing network with Explicitly-decoupled text transfer and Minimized background reconstruction, called STEEM. Unlike existing methods that usually fuse text style, text content, and background, our approach focuses on decoupling text style and content from the background and utilizes the minimized background reconstruction to reduce the impact of text replacement on the background. Specifically, the text-background separation module predicts the text mask of the scene text image, separating the source text from the background. Subsequently, the style-guided text transfer decoding module transfers the geometric and stylistic attributes of the source text to the content text, resulting in the target text. Next, the background and target text are combined to determine the minimal reconstruction area. Finally, the context-focused background reconstruction module is applied to the reconstruction area, producing the editing result. Furthermore, to ensure stable joint optimization of the four modules, a task-adaptive training optimization strategy has been devised. Experimental evaluations conducted on two popular datasets demonstrate the effectiveness of our approach. STEEM outperforms state-of-the-art methods, as evidenced by a reduction in the FID index from 29.48 to 24.67 and an increase in text recognition accuracy from 76.8% to 78.8%.

Image Reconstruction for Accelerated MR Scan With Faster Fourier Convolutional Neural Networks.

High quality image reconstruction from undersampled k -space data is key to accelerating MR scanning. Current deep learning methods are limited by the small receptive fields in reconstruction networks, which restrict the exploitation of long-range information, and impede the mitigation of full-image artifacts, particularly in 3D reconstruction tasks. Additionally, the substantial computational demands of 3D reconstruction considerably hinder advancements in related fields. To tackle these challenges, we propose the following: 1) A novel convolution operator named Faster Fourier Convolution (FasterFC), aims at providing an adaptable broad receptive field for spatial domain reconstruction networks with fast computational speed. 2) A split-slice strategy that substantially reduces the computational load of 3D reconstruction, enabling high-resolution, multi-coil, 3D MR image reconstruction while fully utilizing inter-layer and intra-layer information. 3) A single-to-group algorithm that efficiently utilizes scan-specific and data-driven priors to enhance k -space interpolation effects. 4) A multi-stage, multi-coil, 3D fast MRI method, called the faster Fourier convolution based single-to-group network (FAS-Net), comprising a single-to-group k -space interpolation algorithm and a FasterFC-based image domain reconstruction module, significantly minimizes the computational demands of 3D reconstruction through split-slice strategy. Experimental evaluations conducted on the NYU fastMRI and Stanford MRI Data datasets reveal that the FasterFC significantly enhances the quality of both 2D and 3D reconstruction results. Moreover, FAS-Net, characterized as a method that can achieve high-resolution (320, 320, 256), multi-coil, (8 coils), 3D fast MRI, exhibits superior reconstruction performance compared to other state-of-the-art 2D and 3D methods.

Unsupervised fabric defect detection based on multiscale image reconstruction and structural similarity assessment

AbstractFabric defect detection is a crucial aspect of the textile industry. Currently, deep learning methods have demonstrated exceptional performance in fabric defect detection tasks. However, their performance is greatly affected by the number of defect samples, which is a challenge to obtain during actual production. To address this issue, this article proposes an unsupervised anomaly detection method for fabric defects using image reconstruction networks. This method only requires defect‐free samples for training. During the training phase, the model compresses defect‐free samples to obtain a low‐dimensional manifold and reconstruct them. During the inference phase, the method assesses whether a sample is defective by calculating the reconstruction error between the input and output images, and locates the defect region by computing the difference in various patches. Furthermore, since fabric contains rich texture features, with high correlation between neighbouring pixels, a structure similarity index measure combined with mean absolute error is introduced to evaluate the reconstruction error, which enhances the model's representation ability for defect‐free samples. Additionally, considering the diverse texture backgrounds in fabric, a multiscale reconstruction module is designed to optimise the reconstruction effect. Experimental results demonstrate that compared with other related approaches, the proposed method achieves high accuracy (image‐based area under the curve (AUC) up to 98.2% and pixel‐based AUC up to 97.3%) on multiple datasets and has good generalisation ability for different fabric textures.

A fine-grained feature decoupling based multi-source domain adaptation network for rotating machinery fault diagnosis

Multi-source domain adaptation, an effective solution for rotating machinery fault diagnosis, has achieved great success. However, previous multi-source domain adaptation based methods typically achieve domain consistency by aligning the global distribution of the source and target domains, regardless of private domain information and sufficient feature transferability, thereby limiting the diagnosis performance in cross-domain diagnostic scenarios. To address these issues, we propose a novel fine-grained feature decoupling based multi-source domain adaptation network (FD-MDAN) for fault diagnosis. Leveraging fine-grained feature decoupling, our FD-MDAN weakens specific features with private domain information and reinforces invariant features with diverse transferability at both of domain and category levels. We further develop a diversity regular term to minimize the feature redundancy, enhancing the transferability. In addition, to ensure that these decoupled features retain representative information of the original data, a reconstruction module is designed to make the reconstructed data and the original data consistent. Extensive experiments are conducted on three rotating machinery datasets. Benefiting from these components, our proposed FD-MDAN demonstrates state-of-the-art performance on various transfer diagnosis tasks.

FedAFR: Enhancing Federated Learning with adaptive feature reconstruction

Federated learning is a distributed machine learning method where clients train models on local data to ensure that data will not be transmitted to a central server, providing unique advantages in privacy protection. However, in real-world scenarios, data between different clients may be non-Independently and Identically Distributed (non-IID) and imbalanced, leading to discrepancies among local models and impacting the efficacy of global model aggregation. To tackle this issue, this paper proposes a novel framework, FedARF, designed to improve Federated Learning performance by adaptively reconstructing local features during training. FedARF offers a simple reconstruction module for aligning feature representations from various clients, thereby enhancing the generalization capability of cross-client aggregated models. Additionally, to better adapt the model to each client’s data distribution, FedARF employs an adaptive feature fusion strategy for a more effective blending of global and local model information, augmenting the model’s accuracy and generalization performance. Experimental results demonstrate that our proposed Federated Learning method significantly outperforms existing methods in variety image classification tasks, achieving faster model convergence and superior performance when dealing with non-IID data distributions.

Reconstruction mammaire secondaire unilatérale par lambeau dorsal pédiculé épargnant le muscle grand dorsal (TDAP et MSLD) chez les patientes aux antécédents de mastectomie totale pour cancer du sein. Étude observationnelle monocentrique

The use of pedicled dorsal flaps sparing the latissimus dorsi muscle (TDAP and MSLD flap) is a well-described reconstruction method in breast reconstruction after breast cancer. However, little data exists regarding patient satisfaction after this surgery. The main objective of this study was to evaluate patient satisfaction after unilateral total secondary breast reconstruction using a TDAP or MSLD flap. The secondary objectives corresponded to the evaluation of postoperative complications following this surgery, the evaluation of the duration of the reconstruction and the nature of additional interventions, the evaluation of the functional after-effects, and the evaluation of the chest size when the reconstruction is completed. This is a monocentric, retrospective cohort study, including 22 patients who underwent unilateral secondary total breast reconstruction using a TDAP or MSLD flap between January 1, 2018 and December 31, 2022. Patient satisfaction was assessed using three questionnaires validated in breast reconstruction: the Reconstruction module of the BREAST-Q, the MBROS-S and the MBROS-BI. The MBROS-S satisfaction score is 71.4%. The MBROS-BI body image score is 62%. With the BREAST-Q, the Satisfaction with Breast score is estimated at 53.1; the Satisfaction with Back score is estimated at 75.5; the physical well-being score regarding the chest is evaluated at 71.7; the physical well-being score concerning the shoulder and back is evaluated at 67.4; the psychosocial well-being score is assessed at 67.4; the sexual well-being score is estimated at 48.7; and for women who have benefited from reconstruction associated with a prosthesis, the satisfaction score regarding the implant is 71.6. Unilateral total secondary breast reconstruction with a dorsal pedicled flap sparing the latissimus dorsi muscle is an elegant, reliable, and respectful way to reconstruct a breast, and appears to give high levels of satisfaction.

Accumulation and Elimination: A Hard Decision-Based Multi-User Interference Cancellation Method in Satellite Communication System

With the increasing number of users in the Medium-Orbit (MEO) satellite communication system, multi-access interference (MAI) has become an important factor that restricts the reliability and capacity of the system. Additionally, the low carrier-power-to-noise-density ratio (C/N0) resulting from long-distance transmission poses a significant concern. The parallel interference cancellation (PIC) algorithm, utilized within the paradigm of multi-user detection (MUD), exhibits the capability to effectively mitigate the impact of MAI within the same system. Simultaneously, coherent accumulation serves as a means to substantially enhance the correct detection probability (Pcd) at low C/N0. In this study, a signal acquisition method for multi-user spread spectrum satellite receivers is proposed, which employs interference cancellation and coherent accumulation as its core mechanisms. Furthermore, we introduce a power estimation method based on the outcomes of signal acquisition, which can be integrated into the signal reconstruction module of PIC. Finally, we implement the aforementioned algorithms in both simulation and hardware platforms. Remarkably, we observe that when the interference-to-signal ratio (ISR) caused by MAI equals 20 dB, the improved algorithm attains a maximum Pcd of 0.95 within the high signal-to-noise ratio (SNR) region, closely approaching the theoretical limit for the bit error rate (BER). The experimental results prove the effectiveness and feasibility of the acquisition algorithm. In summary, the enhanced algorithm holds vast potential for widespread implementation in multi-user spread spectrum communication systems.

RepECN: Making ConvNets Better Again for Efficient Image Super-Resolution

RepECN: Making ConvNets Better Again for Efficient Image Super-Resolution

Classification of neuronal morphology based on feature reconstruction and self-cure residual networks

Aiming at the problem of high morphological similarity between the different types of neurons and the large intra-class difference, which is easy to lead to low accuracy of neuron classification, a neural morphology classification method based on feature reconstruction and self-cure residual network is proposed. Firstly, to address the problems of edge pixel weakening and feature erosion by padding strategies that tend to occur during the convolution process of conventional convolution, a feature reconstruction module is constructed at the back end of the backbone network to retain important central features and filter damaged edge features. Then, the attention to neuronal morphological features is enhanced by using a self-attentive weight module and a rank regularization loss method, where the self-attention weight module assigns a weight to each sample to capture the sample importance for weighted loss. In addition, the rank regularization module re-ranked these weights in descending order, dividing them into two groups of high and low weights and regularizing the two groups by enforcing margins between the two average weights. The method achieved superior classification results on the NeuroMorpho-rat dataset, with twelve-way classification accuracies of 96.7%, 86.94% and 85.84% on the Img_raw, Img_resample and Img_XYalign datasets, separately. Comparing with the other methods, the present method has a higher classification accuracy of neurons. Comparing with the original ResNet18 network, it can effectively improve the neuron classification accuracy.