Adjacent Features Research Articles

SMINet:Semantics-aware multi-level feature interaction network for surface defect detection

To boost the product quality, numerous saliency-based surface defect detection methods have been devoted to the areas of industrial production, construction consumable, road construction. However, the existing salient object detection (SOD) methods not only consume a significant amount of computing resources but also fail to meet the detection efficiency requirements of enterprises. Therefore, this paper proposes a lightweight semantics-aware multi-level feature interaction network (SMINet), to address the above issues. In the encoder phase, we integrate multiple adjacent level features in the cross-layer feature fusion (CFF) module to alleviate the discrepancy between multi-scale features. In the decoder phase, we first employ the semantic-aware feature extraction (SFE) module to mine the location cues embedded in the high-level features. Afterwards, we introduce the detail-aware context attention (DCA) module based on the attention mechanism to recover more spatial details. Extensive experiments on four surface defect datasets validate that our SMINet outperforms the existing state-of-the-art methods.

Patch merging refiner embedding UNet for image denoising

Image denoising is a fundamental task in low-level computer vision. The well-known CNN-UNet model with encoder and decoder has shown excellent denoising performance. The encoder adopts downsample modules such as pooling, convolution and patch merging to reduce the feature map size. The downsample module is very important for feature transformation between adjacent feature layers. However, these plain downsample modules are incapable of removing noise during feature transformation. It is expected that the downsample module can play the role of removing noise while executing feature transformation. Therefore, we design a patch merging refiner (PMR) downsample module, which utilizes subspace projection to learn a set of restoration basis from the feature space and projects the patch merging feature onto such space, to remove noise and retain the authentic information of feature space while executing feature transformation. Subsequently, from the perspective of the non-local mechanism, we carry out group convolution (GC) block module on PMR to restore high-frequency detail. Finally, by integrating the two modules into the commonly-used UNet model, we construct a PMR-UNet architecture. Experiments on synthetic and real-world noise images demonstrate that our architecture has stronger anti-noise power and surpasses the state-of-the-art denoisers in both quantitative measure and visual perception.

AFSFusion: An Adjacent Feature Shuffle Combination Network for Infrared and Visible Image Fusion

To obtain fused images with excellent contrast, distinct target edges, and well-preserved details, we propose an adaptive image fusion network called the adjacent feature shuffle-fusion network (AFSFusion). The proposed network adopts a UNet-like architecture and incorporates key refinements to enhance network architecture and loss functions. Regarding the network architecture, the proposed two-branch adjacent feature fusion module, called AFSF, expands the number of channels to fuse the feature channels of several adjacent convolutional layers in the first half of the AFSFusion, enhancing its ability to extract, transmit, and modulate feature information. We replace the original rectified linear unit (ReLU) with leaky ReLU to alleviate the problem of gradient disappearance and add a channel shuffling operation at the end of AFSF to facilitate information interaction capability between features. Concerning loss functions, we propose an adaptive weight adjustment (AWA) strategy to assign weight values to the corresponding pixels of the infrared (IR) and visible images in the fused images, according to the VGG16 gradient feature response of the IR and visible images. This strategy efficiently handles different scene contents. After normalization, the weight values are used as weighting coefficients for the two sets of images. The weighting coefficients are applied to three loss items simultaneously: mean square error (MSE), structural similarity (SSIM), and total variation (TV), resulting in clearer objects and richer texture detail in the fused images. We conducted a series of experiments on several benchmark databases, and the results demonstrate the effectiveness of the proposed network architecture and the superiority of the proposed network compared to other state-of-the-art fusion methods. It ranks first in several objective metrics, showing the best performance and exhibiting sharper and richer edges of specific targets, which is more in line with human visual perception. The remarkable enhancement in performance is ascribed to the proposed AFSF module and AWA strategy, enabling balanced feature extraction, fusion, and modulation of image features throughout the process.

Altered Region Identification in Image Files using Copy-Move Forgery Detection Technique

Nowadays, digital images and videos have high importance because they have become the primary carriers of information. However, the easy availability of powerful image editing software has made it possible to manipulate and edit digital images and videos, leading to a loss of trust in their authenticity. It is possible to add or remove important features from an image without leaving any obvious traces of tampering. To detect this such type of forgeries, the proposed method involves dividing the image into overlapping blocks of the same size, extracting a feature for each block, and representing it as a vector. The vectors are then sorted using radix sort, and the difference in the positions of adjacent feature vectors in the sorted list is computed to obtain a shift vector. This method can even identify tampered parts of an image that have been enhanced or retouched to merge with the background or saved in a lossy format like JPEG. Several forged images were tested to demonstrate the effectiveness of this proposed method. Its application has significant implications in fields like forensics, journalism, and medical imaging to ensure the authenticity of digital images and videos.

A novel multi-attention, multi-scale 3D deep network for coronary artery segmentation.

Automatic segmentation of coronary arteries provides vital assistance to enable accurate and efficient diagnosis and evaluation of coronary artery disease (CAD). However, the task of coronary artery segmentation (CAS) remains highly challenging due to the large-scale variations exhibited by coronary arteries, their complicated anatomical structures and morphologies, as well as the low contrast between vessels and their background. To comprehensively tackle these challenges, we propose a novel multi-attention, multi-scale 3D deep network for CAS, which we call CAS-Net. Specifically, we first propose an attention-guided feature fusion (AGFF) module to efficiently fuse adjacent hierarchical features in the encoding and decoding stages to capture more effectively latent semantic information. Then, we propose a scale-aware feature enhancement (SAFE) module, aiming to dynamically adjust the receptive fields to extract more expressive features effectively, thereby enhancing the feature representation capability of the network. Furthermore, we employ the multi-scale feature aggregation (MSFA) module to learn a more distinctive semantic representation for refining the vessel maps. In addition, considering that the limited training data annotated with a quality golden standard are also a significant factor restricting the development of CAS, we construct a new dataset containing 119 cases consisting of coronary computed tomographic angiography (CCTA) volumes and annotated coronary arteries. Extensive experiments on our self-collected dataset and three publicly available datasets demonstrate that the proposed method has good segmentation performance and generalization ability, outperforming multiple state-of-the-art algorithms on various metrics. Compared with U-Net3D, the proposed method significantly improves the Dice similarity coefficient (DSC) by at least 4% on each dataset, due to the synergistic effect among the three core modules, AGFF, SAFE, and MSFA. Our implementation is released at https://github.com/Cassie-CV/CAS-Net.

RLAT: Multi-hop temporal knowledge graph reasoning based on Reinforcement Learning and Attention Mechanism

Temporal knowledge graphs (TKGs) have been widely used in artificial intelligence but are usually incomplete. Recently, researchers have proposed reasoning methods to infer missing relations in TKGs. TKG reasoning is mainly divided into single-hop reasoning and multi-hop reasoning. Multi-hop reasoning takes the semantics of facts into account. However, multi-hop reasoning methods of TKGs lack a path memory component, and the reasoning results depend on good training. In addition, different adjacent feature information is assigned the same weight, which makes it difficult to distinguish their importance to the central entity. We propose a multi-hop reasoning model combining Reinforcement Learning with the ATtention mechanism (RLAT) to solve the above limitations. First, we use LSTM and attention mechanism as memory components, which are helpful to train multi-hop reasoning paths. Second, an attention mechanism with an influence factor is proposed. This mechanism measures the influence of neighbor information and provides different feature vectors. The strategy function obtained makes the agent focus on occurring relations with high frequency and then reasons multi-hop reasoning paths with higher correlation. Experimental results demonstrate that our approach outperforms most metrics compared to recent efforts.

Cross-level Feature Aggregation Network for Polyp Segmentation

Accurate segmentation of polyps from colonoscopy images plays a critical role in the diagnosis and cure of colorectal cancer. Although effectiveness has been achieved in the field of polyp segmentation, there are still several challenges. Polyps often have a diversity of size and shape and have no sharp boundary between polyps and their surrounding. To address these challenges, we propose a novel Cross-level Feature Aggregation Network (CFA-Net) for polyp segmentation. Specifically, we first propose a boundary prediction network to generate boundary-aware features, which are incorporated into the segmentation network using a layer-wise strategy. In particular, we design a two-stream structure based segmentation network, to exploit hierarchical semantic information from cross-level features. Furthermore, a Cross-level Feature Fusion (CFF) module is proposed to integrate the adjacent features from different levels, which can characterize the cross-level and multi-scale information to handle scale variations of polyps. Further, a Boundary Aggregated Module (BAM) is proposed to incorporate boundary information into the segmentation network, which enhances these hierarchical features to generate finer segmentation maps. Quantitative and qualitative experiments on five public datasets demonstrate the effectiveness of our CFA-Net against other state-of-the-art polyp segmentation methods. The source code and segmentation maps will be released at https://github.com/taozh2017/CFANet.

Contrastive structure and texture fusion for image inpainting

Most recent U-Net based models have shown promising results for the challenging tasks in image inpainting field. However, they often generate content with blurred textures and distorted structures due to the lack of semantic consistency and texture continuity in the missing regions. In this paper, we propose to restore the missing areas at both structural and textural levels. Our method is built upon a U-Net structure, which repairs images by extracting semantic information from high to low resolution and then decoding it back to the original image. Specifically, we utilize the high-level semantic features learned in encoder to guide the inpainting of structure-aware features of its adjacent low-level feature map. Meanwhile, low-level feature maps have clearer texture compared with high-level ones, which can be used as a prior for textural repair of high-level feature maps. subsequently, a module is used to fuse the two repaired feature maps (i.e., structure-aware and texture-aware features) reasonably and obtain a feature map with reasonable semantics. Moreover, in order to learn more representative high-level semantics feature, we design the model as a siamese network for contrastive learning. Experiments on practical data show that our method outperforms other state-of-the-art methods.

RAFNet: Restricted attention fusion network for sleep apnea detection

Sleep apnea (SA) is a common sleep-related breathing disorder, which would lead to damage of multiple systemic organs or even sudden death. In clinical practice, portable device is an important tool to monitor sleep conditions and detect SA events by using physiological signals. However, SA detection performance is still limited due to physiological signals with time-variability and complexity. In this paper, we focus on SA detection with single lead ECG signals, which can be easily collected by a portable device. Under this context, we propose a restricted attention fusion network called RAFNet for sleep apnea detection. Specifically, RR intervals (RRI) and R-peak amplitudes (Rpeak) are generated from ECG signals and divided into one-minute-long segments. To alleviate the problem of insufficient feature information of the target segment, we combine the target segment with two pre- and post-adjacent segments in sequence, (i.e. a five-minute-long segment), as the input. Meanwhile, by leveraging the target segment as the query vector, we propose a new restricted attention mechanism with cascaded morphological and temporal attentions, which can effectively learn the feature information and depress redundant feature information from the adjacent segments with adaptive assigning weight importance. To further improve the SA detection performance, the target and adjacent segment features are fused together with the channel-wise stacking scheme. Experiment results on the public Apnea-ECG dataset and the real clinical FAH-ECG dataset with sleep apnea annotations show that the RAFNet greatly improves SA detection performance and achieves competitive results, which are superior to those achieved by the state-of-the-art baselines.

A smart and flexible approach for aggregation of adjacent polygons to meet a minimum target area or attribute value

Many geospatial analyses require flexible aggregation of adjacent units to meet a minimum target area or attribute value. This is usually accomplished using several non-automated and complex GIS tasks. We developed an integrated user-friendly approach and algorithm implemented in the ‘GHS-SmartDissolve’ tool, which addresses minimum mapping unit or attribute value requirements, layers resolution mismatch, spatial uncertainty or modifiable areal unit problem in GIScience. This method automatically dissolves adjacent features updating fields’ values to reach a minimum target area or attribute value, using a flexible settings framework to meet user requirements. Also provided as a toolbox for ArcGIS (Esri), the approach is demonstrated by (i) estimating the mean particulate matter concentrations for all municipalities in Italy in 2011 by combining a coarse grid of global PM2.5 concentrations with fine administrative units; (ii) estimating boundaries of Metropolitan areas in Portugal as aggregation of municipalities, by matching their total population.

An integrated analysis of transport, oxidation, and creep during oxidation of interior pores in SiC

AbstractOxidation of SiC plays a critical role in the durability of ceramic matrix composites, as large changes in molar volume generate significant stresses that can drive cracking in adjacent features. The analysis of such phenomena requires coupling between descriptions of diffusion through the oxide, growth of the oxide domain (i.e., evolution of the oxide/SiC interface), and creep relaxation in the oxide at elevated temperatures. This paper presents a two‐dimensional finite element framework that uses a single finite element mesh to predict these behaviors; large changes in the oxide geometry are simulated by tracking the oxidation front as a discrete interface and periodically re‐meshing. The numerical performance of the framework is illustrated using an analytical description of oxidation of a flat surface and subsequent stress evolution. The framework is then used to analyze internal oxidation within a cylindrical cavity for a wide range of temperatures and water vapor concentrations pertinent to gas turbines. The results are used to discuss the roles of oxide growth rate, creep, and geometry with respect to the tensile stresses that develop in the adjacent SiC, and their implications for oxidation‐driven damage at high temperatures.

Point cloud upsampling generative adversarial network based on residual multi-scale off-set attention

BackgroundOwing to the limitations of the working principle of three-dimensional (3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. MethodIn this paper, we propose a new generative adversarial network (GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention (SA) module with an implicit Laplacian offset attention (OA) module and to aggregate the adjacency features using a multiscale offset attention (MSOA) module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention (RMSOA) module, which utilizes multiscale structural relationships to generate finer details. ResultThe results of several experiments show that our method outperforms existing methods and is highly robust.

A deep learning approach for brain tumor detection using magnetic resonance imaging

The growth of abnormal cells in the brain’s tissue causes brain tumors. Brain tumors are considered one of the most dangerous disorders in children and adults. It develops quickly, and the patient’s survival prospects are slim if not appropriately treated. Proper treatment planning and precise diagnoses are essential to improving a patient’s life expectancy. Brain tumors are mainly diagnosed using magnetic resonance imaging (MRI). As part of a convolution neural network (CNN)-based illustration, an architecture containing five convolution layers, five max-pooling layers, a Flatten layer, and two dense layers has been proposed for detecting brain tumors from MRI images. The proposed model includes an automatic feature extractor, modified hidden layer architecture, and activation function. Several test cases were performed, and the proposed model achieved 98.6% accuracy and 97.8% precision score with a low cross-entropy rate. Compared with other approaches such as adjacent feature propagation network (AFPNet), mask region-based CNN (mask RCNN), YOLOv5, and Fourier CNN (FCNN), the proposed model has performed better in detecting brain tumors.

A long-memory pedestrian target tracking algorithm incorporating spatiotemporal trajectory feature enhancement model

Multi-target tracking is a complex problem in computer vision, involving occlusion, target trajectory disappearance, etc. In response to these questions, we first propose a trajectory coordinate bi-directional sensing attention module (BasicCaModule). This module enables the network to be more focused on essential areas. Secondly, we propose the Feature Confusion Edge Enhancement (FCEE) module, which enhances the confusion region of adjacent feature edges. After detecting the network output feature map, we propose the adaptive feature separation header (FDH) module. This module can activate essential features adaptively to reduce the number of target identity switches. Finally, appropriate hyperparameters are set and optimized for the ByteTrack tracking algorithm, resolving fragment tracking loss and long memory matching problems. After a large amount of experimental data, our approach is highly competitive with the existing state-of-the-art algorithms. Moreover, it can also keep online tracking while maintaining high tracking accuracy. The code is publicly available at: https://github.com/CccJ23/Spatio-temporal-trajectory-Tracking

MDCT: Multi-Kernel Dilated Convolution and Transformer for One-Stage Object Detection of Remote Sensing Images

Deep learning (DL)-based object detection algorithms have gained impressive achievements in natural images and have gradually matured in recent years. However, compared with natural images, remote sensing images are faced with severe challenges due to the complex backgrounds and difficult detection of small objects in dense scenes. To address these problems, a novel one-stage object detection model named MDCT is proposed based on a multi-kernel dilated convolution (MDC) block and transformer block. Firstly, a new feature enhancement module, MDC block, is developed in the one-stage object detection model to enhance small objects’ ontology and adjacent spatial features. Secondly, we integrate a transformer block into the neck network of the one-stage object detection model in order to prevent the loss of object information in complex backgrounds and dense scenes. Finally, a depthwise separable convolution is introduced to each MDC block to reduce the computational cost. We conduct experiments on three datasets: DIOR, DOTA, and NWPU VHR-10. Compared with the YOLOv5, our model improves the object detection accuracy by 2.3%, 0.9%, and 2.9% on the DIOR, DOTA, and NWPU VHR-10 datasets, respectively.

Теоретичні підходи до визначення поняття та сутності етнографічного туризму

Today, it is acute the issue of preserving ethno-cultural heritage and the diversity of peoples, ethnic groups and tribal communities. In addition to the processes of globalization, scientific and technical development and the growth of information loads, the Covid-19 pandemic, the military invasion of the territory of Ukraine, natural and anthropogenic cataclysms had no less impact on the tourism industry and on preserving the unique peoples’ culture. As a result, among consumers of tourist services, there are increased attention to their safety during travel and interest in their own roots, culture and traditions, as well as in the cultures and identity of other peoples. This, in turn, caused for popularity growth of tours with ethnographic elements. Nevertheless, ethnographic tourism is still an understudied part of the modern tourism industry. That is why in the paper provides a monographic analysis of the essence and approaches to defining the concept of «ethnographic tourism». Also, there are revealed the peculiarities of ethnographic tourism. There have been highlighted differences of ethnographic tourism among such types of tourism as ethnocultural, ethnic, nostalgic, ethno-educational, ecological-ethnographic and anthropological. It was determined that the concept of ethnographic tourism is broader, unlike the above-mentioned concepts, and includes certain features of each of this types of tourism. The author proposed his own interpretation of ethnographic tourism concept, according to which ethnographic tourism is a type of tourism that has adjacent features with cultural-cognitive, ethnic, ethno-cultural, nostalgic, ethno-cognitive, ecological-ethnographic and anthropological types of tourism, the objects of which often overlap, and the main purpose of which is to learn about the ethno-cultural heritage of the visited area.

Two-Stage Hybrid Deep Learning With Strong Adaptability for Detailed Day-Ahead Photovoltaic Power Forecasting

Deep learning (DL) has been widely used in photovoltaic (PV) power forecasting due to its advantages in nonlinear processing and feature extraction. However, it faces an overfitting challenge when daily weather change, resulting in poor adaptability for practical applications. Conversely, the mapping strategy primarily applied in plant sacrifices the PV power fluctuation details for forecasting under complex weather conditions to improve adaptation. To keep long-term adaptations and accurately forecast fluctuation detail, this study proposes a novel two-stage hybrid DL (HDL) framework for day-ahead PV power forecasting with 15-min intervals. In the first numerical weather prediction (NWP) information mapping stage, motivated by forecasting strategies in plants, a mapping model is developed based on long short-term memory (LSTM) networks to forecast the general power trends with strong adaptation. Then, in the second stage of historical features (adjacency and similarity features) extraction, wavelet decomposition, LSTM, and a convolutional neural network are used to forecast more fluctuation details accurately. Moreover, a hyperparameter optimization method based on grid search and Bayesian optimization is proposed, which facilitates an unbiased development of DL. The developed framework is implemented on 10 MW and 100 kW plants and the results show that the proposed method can achieve correctness and adaptation among the rivals.

A Lightweight Segmented Attention Network for Sleep Staging by Fusing Local Characteristics and Adjacent Information.

Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole epoch or adjacent epochs, ignoring the local signal variations within epoch. To address these issues, a novel deep learning architecture named segmented attention network (SAN) is proposed in this paper. The architecture can be divided into feature extraction (FE) and time sequence encoder (TSE). The FE module consists of multiple multiscale CNN (MMCNN) and residual squeeze and excitation block (SE block). The former extracts features from multiple equal-length EEG segments and the latter reinforced the features. The TSE module based on a multi-head attention mechanism could capture the temporal information in the features extracted by FE module. Noteworthy, in SAN, we replaced the RNN module with a TSE module for temporal learning and made the network faster. The evaluation of the model was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDFX, and one clinical dataset from Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed model achieved the accuracy of 85.5%, 86.4%, 82.5% on Sleep-EDFX, MASS and HSFU, respectively. The experimental results exhibited favorable performance and consistent improvements of SAN on different datasets in comparison with the state-of-the-art studies. It also proved the necessity of sleep staging by integrating the local characteristics within epochs and adjacent informative features among epochs.

PCCN: Progressive Context Comprehension Network for Oil Stains Detection of High-Speed Trains

Oil plays an important role in the gearbox, traction transformer, hydraulic damper, and other key components of high-speed trains. Once oil leakage occurs, it indicates that some faults may happen and even affect the normal operation of high-speed trains, thus posing a threat to the safety of the train. Therefore, we can detect the oil stains to discover leaks or find some faults in these components to eliminate potential threats in time. Oil stains have the properties of irregular shapes and huge differences in size, and the internal environment of the train is complex and composed of various parts so it is difficult to detect oil stains. This paper proposes a novel methodology to detect oil stains, named Progressive Context Comprehension Network(PCCN). The Upsampling Augmentation Module(UAM) and Feature Refinement Module(FRM) are proposed to augment features by strengthening the long short-term contextual relationship of features from multi-levels. The Pyramid Context Fusion Module(PCFM) is proposed to fuse features by progressively integrating adjacent features, which makes features of each level richer. Moreover, a loss function is applied to instruct the network to learn the characteristics of oil stains in the case of extremely uneven distribution of oil stains and background. Experiment results show that our network achieves better performance such as mIoU and F1-Score with a minimal number of parameters and FLOPs than advanced semantic segmentation methods. Besides, we apply our proposed network to five public saliency datasets and achieve better performance, which demonstrates the adaptability and effectiveness of our method as well.

Adjacent Complementary Network for Salient Object Detection in Optical Remote Sensing Images

Salient object detection in optical remote sensing images (RSI-SOD) is a newly developing task and has attracted extensive attention. Although some satisfactory performances have been achieved, there are still some poor performance situations, such as complex backgrounds and objects with various scales. Because the existing methods have the issue of insufficient adjacent feature representation and inappropriate constraint supervision. To alleviate the issues, we attempt to utilize the adjacent complementary and introduce the global constraints. Accordingly, we propose the adjacent complementary network (ACNet) with global constraints for RSI-SOD. Specifically, in the encoder, we mainly design the adjacent complementary module (ACM) to complement the features among the current layer and adjacent layers. Therefore, it can effectively aggregate saliency features. Besides, we have equipped a global average pooling (GAP) to enhance global information. In the decoder, we design a fusion enhancement module (FEM) to enhance the feature conversion between the coding layer and decoding layer. Finally, we employ a novel loss, which introduces global constraints and can supervise the objects with various scales. Extensive studies on two benchmark datasets demonstrate that ACNet is competitive and outperforms the 15 state-of-the-art (SOTA) approaches.