Detail Information Research Articles

A color image decomposition model for image enhancement

The primary goal of image decomposition is to decompose an observed image into several independent components, which can be further manipulated to carry out more complex tasks effectively. Existing image decomposition methods apply a decomposition model either to each of the three channels separately in RGB color space, or to the intensity channel only in other color spaces, which leads to color error or unintuitive display. To address these issues, this paper proposes a color image decomposition model that acts directly on color images and yields visually piecewise smoothing base information, low/high contrast detail information, and rich color information. Specifically, the color information with characteristics of spherical geometry is separated by a spatial transformation at first. Then, the separation of base and detail information from a given image is achieved by combining low-rank approximation and the relative total variation with no artifacts. After yielding the three components via our decomposition model, we exploit the automatic arc tangent transformation and the visual saliency principle to implement two applications, contrast enhancement and infrared image fusion, respectively. We demonstrate the remarkable performance of our method through a reasonable qualitative and quantitative analysis of the experimental results.

Mapping of decentralised photovoltaic and solar thermal systems by remote sensing aerial imagery and deep machine learning for statistic generation

As a mean to monitor the rapid expansion of the highly decentralized PV market, identifying solar energy systems in aerial imagery by deep machine learning, is a research field that is getting increasing interest. One general challenge in the field is to create testing data of high quality that are representative of the end-use application. In this study we use the open source convolutional neural network developed within the DeepSolar project and apply it in the country of Sweden, for the purpose of generating market statistics, by scanning three complete municipalities for small decentralized photovoltaic and solar thermal systems. The evaluation of the performance is done against a highly accurate ground truth, which was created by cross-checking the classification results with the inventory of the local distribution system operators and the database of photovoltaic systems that have received a capital subsidy in Sweden, and combining that with physical onsite inspections. A process of generate additional training data and re-training the algorithm after each municipality scan was developed, which successively improved the accuracy, resulting in that 95% of all detectable photovoltaic, excluding building integrated and vertical systems, and 80% of all detectable solar thermal systems were correctly identified in the last municipality scan. The accurate ground truth allowed a quantification of why some systems are not detected. The generated dataset of solar energy systems could be connected to existing building and property inventories, which allowed creation of market segment statistics with remarkably high detail information.

PCB Defect Detection via Local Detail and Global Dependency Information.

Due to the impact of the production environment, there may be quality issues on the surface of printed circuit boards (PCBs), which could result in significant economic losses during the application process. As a result, PCB surface defect detection has become an essential step for managing PCB production quality. With the continuous advancement of PCB production technology, defects on PCBs now exhibit characteristics such as small areas and diverse styles. Utilizing global information plays a crucial role in detecting these small and variable defects. To address this challenge, we propose a novel defect detection framework named Defect Detection TRansformer (DDTR), which combines convolutional neural networks (CNNs) and transformer architectures. In the backbone, we employ the Residual Swin Transformer (ResSwinT) to extract both local detail information using ResNet and global dependency information through the Swin Transformer. This approach allows us to capture multi-scale features and enhance feature expression capabilities.In the neck of the network, we introduce spatial and channel multi-head self-attention (SCSA), enabling the network to focus on advantageous features in different dimensions. Moving to the head, we employ multiple cascaded detectors and classifiers to further improve defect detection accuracy. We conducted extensive experiments on the PKU-Market-PCB and DeepPCB datasets. Comparing our proposed DDTR framework with existing common methods, we achieved the highest F1-score and produced the most informative visualization results. Lastly, ablation experiments were performed to demonstrate the feasibility of individual modules within the DDTR framework. These experiments confirmed the effectiveness and contributions of our approach.

A Deep Learning Network for Individual Tree Segmentation in UAV Images with a Coupled CSPNet and Attention Mechanism

Accurate individual tree detection by unmanned aerial vehicles (UAVs) is a critical technique for smart forest management and serves as the foundation for evaluating ecological functions. Existing object detection and segmentation methods, on the other hand, have reduced accuracy when detecting and segmenting individual trees in complicated urban forest landscapes, as well as poor mask segmentation quality. This study proposes a novel Mask-CSP-attention-coupled network (MCAN) based on the Mask R-CNN algorithm. MCAN uses the Cross Stage Partial Net (CSPNet) framework with the Sigmoid Linear Unit (SiLU) activation function in the backbone network to form a new Cross Stage Partial Residual Net (CSPResNet) and employs a convolutional block attention module (CBAM) mechanism to the feature pyramid network (FPN) for feature fusion and multiscale segmentation to further improve the feature extraction ability of the model, enhance its detail information detection ability, and improve its individual tree detection accuracy. In this study, aerial photography of the study area was conducted by UAVs, and the acquired images were used to produce a dataset for training and validation. The method was compared with the Mask Region-based Convolutional Neural Network (Mask R-CNN), Faster Region-based Convolutional Neural Network (Faster R-CNN), and You Only Look Once v5 (YOLOv5) on the test set. In addition, four scenes—namely, a dense forest distribution, building forest intersection, street trees, and active plaza vegetation—were set up, and the improved segmentation network was used to perform individual tree segmentation on these scenes to test the large-scale segmentation ability of the model. MCAN’s average precision (AP) value for individual tree identification is 92.40%, which is 3.7%, 3.84%, and 12.53% better than that of Mask R-CNN, Faster R-CNN, and YOLOv5, respectively. In comparison to Mask R-CNN, the segmentation AP value is 97.70%, an increase of 8.9%. The segmentation network’s precision for the four scenes in multi-scene segmentation ranges from 95.55% to 92.33%, showing that the proposed network performs high-precision segmentation in many contexts.

Res-SwinTransformer with Local Contrast Attention for Infrared Small Target Detection

Infrared small target detection for aerial remote sensing is crucial in both civil and military fields. For infrared targets with small sizes, low signal-to-noise ratio, and little detailed texture information, we propose a Res-SwinTransformer with a Local Contrast Attention Network (RSLCANet). Specifically, we first design a SwinTransformer-based backbone to improve the interaction capability of global information. On this basis, we introduce a residual structure to fully retain the shallow detail information of small infrared targets. Furthermore, we design a plug-and-play attention module named LCA Block (local contrast attention block) to enhance the target and suppress the background, which is based on local contrast calculation. In addition, we develop an air-to-ground multi-scene infrared vehicle dataset based on an unmanned aerial vehicle (UAV) platform, which can provide a database for infrared vehicle target detection algorithm testing and infrared target characterization studies. Experiments demonstrate that our method can achieve a low-miss detection rate, high detection accuracy, and high detection speed. In particular, on the DroneVehicle dataset, our designed RSLCANet increases by 4.3% in terms of mAP@0.5 compared to the base network You Only Look Once (YOLOX). In addition, our network has fewer parameters than the two-stage network and the Transformer-based network model, which helps the practical deployment and can be applied in fields such as car navigation, crop monitoring, and infrared warning.

Accounting for the management of goods in the customs warehouse

The article analyzes the basic principles of forming a system of accounting for goods in a customs warehouse. In particular, to ensure control over the placement, movement, storage and release of goods, it is proposed to use markings that will allow identification of objects that require special conditions of storage, transportation or customs clearance. A proposal has been put forward to introduce mandatory storage bookkeeping for customs warehouses, which will detail information on available cargo. In addition, it is stated that an important factor in accounting for the management of goods in a customs warehouse is the development of a work plan for off-balance sheet accounts, if the warehouse keeper, by prior agreement, places the cargo of another business entity in its customs warehouse.

Dual Vision Transformer.

Recent advances have presented several strategies to mitigate the computations of self-attention mechanism with high-resolution inputs. Many of these works consider decomposing the global self-attention procedure over image patches into regional and local feature extraction procedures that each incurs a smaller computational complexity. Despite good efficiency, these approaches seldom explore the holistic interactions among all patches, and are thus difficult to fully capture the global semantics. In this paper, we propose a novel Transformer architecture that elegantly exploits the global semantics for self-attention learning, namely Dual Vision Transformer (Dual-ViT). The new architecture incorporates a critical semantic pathway that can more efficiently compress token vectors into global semantics with reduced order of complexity. Such compressed global semantics then serve as useful prior information in learning finer local pixel level details, through another constructed pixel pathway. The semantic pathway and pixel pathway are integrated together and are jointly trained, spreading the enhanced self-attention information in parallel through both of the pathways. Dual-ViT is henceforth able to capitalize on global semantics to boost self-attention learning without compromising much computational complexity. We empirically demonstrate that Dual-ViT provides superior accuracy than SOTA Transformer architectures with comparable training complexity. Source codes are available at https://github.com/YehLi/ImageNetModel.

EMA‐GAN: A Generative Adversarial Network for Infrared and Visible Image Fusion with Multiscale Attention Network and Expectation Maximization Algorithm

The purpose of the infrared and visible image fusion is to generate a fused image with rich information. Although most fusion methods can achieve good performance, there are still shortcomings in extracting feature information from source images, which make it difficult to balance the thermal radiation region information and texture detail information in the fused image. To address the above issues, an expectation maximization (EM) learning framework based on adversarial generative networks (GAN) for infrared and visible image fusion is proposed. The EM algorithm (EMA) can obtain maximum likelihood estimation for problems with potential variables, which is helpful in solving the problem of lack of labels in infrared and visible image fusion. The axial‐corner attention mechanism is designed to capture long‐range semantic information and texture information of the visible image. The multifrequency attention mechanism digs the relationships between features at different scales to highlight target information of infrared images in the fused result. Meanwhile, two discriminators are used to balance two different features, and a new loss function is designed to maximize the likelihood estimate of the data with soft class label assignments, which is obtained from the expectation network. Extensive experiments demonstrate the superiority of EMA‐GAN over the state‐of‐the‐art.

Cross-level collaborative context-aware framework for medical image segmentation

Efficient and accurate medical image segmentation is necessary for pathological evaluation and disease diagnosis in clinical practice. In recent years, the U-shaped encoder–decoder structure has achieved good performance in various medical image segmentation tasks. It is a neural network model similar to the letter U, which can gradually reduce the spatial dimension of the feature map to capture high-level semantic information in the feature encoding stage, and can make up for the lack of target detail information in the feature decoding stage to decouple the final segmentation results. However, the U-shaped encoder–decoder structure still suffers from semantic asymmetry and global semantic dilution problems, which are exacerbated during decoding, due to the limitation of the framework’s fixation. In this paper, we propose a cross-level collaborative context-aware framework (C3-Net) to address the aforementioned issues in medical image segmentation. The main contributions of this research include: (i) To address the inherent problems in the U-shaped structure, we propose the C3-Net to explore the differences between cross-level contextual information effectively; (ii) To achieve detailed information preservation and semantic information enhancement, we present a Channel Scale-aware Context Enhancement (CSCE) module to enhance low-level contextual features from the global and local scales of the channel dimension; (iii) A Spatial Pyramid Context Alignment (SPCA) module is designed to extract and align pyramid features, thus obtaining accurate global contextual features at the network’s top; (iv) We propose a Cross-Level Collaborative Context Refinement (CCCR) module to enable efficient collaboration between cross-level contextual features to simultaneously achieve semantic alignment and global semantic enhancement. The outcomes of implementing the proposed method on three publicly available datasets (Synapse, ACDC, and GlaS) and one private dataset (VMICH) show that the proposed method outperforms all competing approaches on four datasets. Our C3-Net achieves new state-of-the-art performance on four image segmentation tasks with Dice scores of 85.26%, 92.10%, 87.20%, and 87.61%, respectively.

Unraveling the impact of ORF3a Q57H mutation on SARS-CoV-2: insights from molecular dynamics

ORF3a is a conserved accessory protein of SARS-CoV-2, linked to viral infection and pathogenesis, with acquired mutations at various locations. Previous studies have shown that the occurrence of the Q57H mutation is higher in comparison to other positions in ORF3a. This mutation is known to induce conformational changes, yet the extent of structural alteration and its role in the viral adaptation process remain unknown. Here we performed molecular dynamics (MD) simulations of wt-ORF3a, Q57H, and Q57A mutants to analyze structural changes caused by mutations compared to the native protein. The MD analysis revealed that Q57H and Q57A mutants show significant structural changes in the dimer conformation than the wt-ORF3a. This dimer conformer narrows down the ion channel cavity, which reduces Na + or K + permeability leading to decrease the antigenic response that can help the virus to escape the host immune system. Non-bonding interaction analysis shows the Q57H mutant has more interacting residues, resulting in more stability within dimer conformation than the wt-ORF3a and Q57A. Moreover, both mutant dimers (Q57H and Q57A) form a novel salt-bridge interaction at the same position between A:Asp142 and B:Lys61, whereas such an interaction is absent in the wt-ORF3a dimer. We have also noticed that the TM3 domain’s flexibility in Q57H is increased because of strong inter-domain interactions of TM1 and TM2 within the dimer conformation. These unusual interactions and flexibility of Q57H mutant can have significant impacts on the SARS-CoV-2 adaptations, virulence, transmission, and immune system evasion. Our findings are consistent with the previous experimental data and provided details information on the structural perturbation in ORF3a caused by mutations, which can help better understand the structural change at the molecular level as well as the reason for the high virulence properties of this variant. Communicated by Ramaswamy H. Sarma

An efficient image defogging algorithm based on dragonfly optimized gamma correction and stationary wavelet decomposition

Image dehazing is a revolutionary technique for restoring images with hazy or foggy landscapes, that has gotten a lot of focus in recent years since it gained importance in a surveillance system. However, the image processing by the traditional defogging algorithm has difficulties in integrating the depth of image detail and the color of the image. Therefore, in this paper, a novel framework based on wavelet decomposition and optimized gamma correction is proposed for efficaciously retrieving the fog-free image. The foggy image is first divided into low and high frequency sub-images using SWT (Stationary Wavelet Transform), which has the advantages of preserving temporal features so that information loss can be stopped. Then the low frequency and high frequency images are processed with defogging and denoising modules to remove fog and noise respectively. The DOGC (Dragonfly optimal Gamma Correction) algorithm in dehazing module dynamically enhanced the color detail information without human intervention so that observed scene contrast and visibility are well preserved. Lastly, fog-free image is reconstructed from sub-enhanced images. The experimental findings show that the proposed framework outperforms state-of-the-art methods in terms of both quantitative and qualitative assessment criteria using the established dataset. Furthermore, the proposed method efficiently removes fog while preserving the naturalness of fog images.

Underwater Target Detection Based on Parallel High-Resolution Networks.

A parallel high-resolution underwater target detection network is proposed to address the problems of complex underwater scenes and limited target feature extraction capability. First, a high-resolution network (HRNet), a lighter high-resolution human posture estimation network, is used to improve the target feature representation and effectively reduce the semantic information lost in the image during sampling. Then, the attention module (A-CBAM) is improved to capture complex feature distributions by modeling the two-dimensional space in the activation function stage through the introduction of the flexible rectified linear units (FReLU) activation function to achieve pixel-level spatial information modeling capability. Feature enhancement in the spatial and channel dimensions is performed to improve understanding of fuzzy targets and small target objects and to better capture irregular and detailed object layouts. Finally, a receptive field augmentation module (RFAM) is constructed to obtain sufficient semantic information and rich detail information to further enhance the robustness and discrimination of features and improve the detection capability of the model for multi-scale underwater targets. Experimental results show that the method achieves 81.17%, 77.02%, and 82.9% mean average precision (mAP) on three publicly available datasets, specifically underwater robot professional contest (URPC2020, URPC2018) and pattern analysis, statistical modeling, and computational learning visual object classes (PASCAL VOC2007), respectively, demonstrating the effectiveness of the proposed network.

Multi-Scale Semantic and Detail Extraction Network for Lightweight Person Re-Identification

Exploring multi-level information to obtain fine-grained features is the key factor to improve the performance of person re-identification (Re-ID). However, existing models for person Re-ID only focus on learning the high-level semantic information while neglecting the low-level detail information. To alleviate this issue, we propose a lightweight person Re-ID method termed Multi-Scale Semantic and Detail Extraction Network (MSDENet) to obtain robustness and discriminative feature representation for the Re-ID task. Specifically, we design a Series Channel-Spatial Attention (SCSA) and embed it into the lightweight backbone network to focus on the key parts of pedestrian images. Meanwhile, we propose a Multi-Scale Semantic and Detail Extraction (MSDE) method to extract multi-scale features of semantic information and detail information, which can effectively capture the feature diversity of pedestrian images. Furthermore, we design a Feature Enhancement Fusion (FEF), which enhances and fuses the fine-grained features of semantic extraction and detail extraction branches to better obtain the discriminative feature representation. Extensive experiments conducted on popular datasets Market1501, MSMT17, and CUHK03 demonstrate that the proposed MSDENet has competitive performance compared with the state-of-the-art methods.

Spatial-Temporal Semantic Perception Network for Remote Sensing Image Semantic Change Detection

Semantic change detection (SCD) is a challenging task in remote sensing, which aims to locate and identify changes between the bi-temporal images, providing detailed “from-to” change information. This information is valuable for various remote sensing applications. Recent studies have shown that multi-task networks, with dual segmentation branches and single change branch, are effective in SCD tasks. However, these networks primarily focus on extracting contextual information and ignore spatial details, resulting in the missed or false detection of small targets and inaccurate boundaries. To address the limitations of the aforementioned methods, this paper proposed a spatial-temporal semantic perception network (STSP-Net) for SCD. It effectively utilizes spatial detail information through the detail-aware path (DAP) and generates spatial-temporal semantic-perception features through combining deep contextual features. Meanwhile, the network enhances the representation of semantic features in spatial and temporal dimensions by leveraging a spatial attention fusion module (SAFM) and a temporal refinement detection module (TRDM). This augmentation results in improved sensitivity to details and adaptive performance balancing between semantic segmentation (SS) and change detection (CD). In addition, by incorporating the invariant consistency loss function (ICLoss), the proposed method constrains the consistency of land cover (LC) categories in invariant regions, thereby improving the accuracy and robustness of SCD. The comparative experimental results on three SCD datasets demonstrate the superiority of the proposed method in SCD. It outperforms other methods in various evaluation metrics, achieving a significant improvement. The Sek improvements of 2.84%, 1.63%, and 0.78% have been observed, respectively.

Capital Budgeting and Financial Investment Appraisal: A Review of Archival Literature

Abstract: Universally, fund raising issues and capital utilitization have been the heart-beat of all financial managers both in the private and public sector. However, profitable utilization of scarce financial resources by various sectors has become more important as cost of fund raised daily has become increasingly astronomical. Hence, the financial manager must do all that is possible to generate returns that will not only be sufficient to meet the cost of funds but also enough to satisfy the wealth maximization objective of the firm. Raising finance for corporate bodies thus becomes important and of highest import. Thus, the aim of this study is to carry out a detailed review of archival literature on the roles of financial management in capital investment appraisal. In this study, the authors intend to review archival literatures to find out the contributions of financial managers in making good financial decisions and to reveal the impact of capital budgeting techniques on financial projects. This simply will provide the reader full detail information about how the necessary data/materials used in the study was collected. The data used for the research were collected by means of vital and relevant data from secondary sources through the review of some related and available documents such as textbooks, term papers, and business publications like magazines, journals, newspaper, periodicals, published and unpublished works and statistical records. This study found that in other to achieve the desired goals of financial managers in effective decision making senior management of any organization must bear in mind that observation of the doctrine of capital investment appraisal must be obeyed and properly executed in the organization.

LPMSNet: Location Pooling Multi-Scale Network for Cloud and Cloud Shadow Segmentation

Among the most difficult difficulties in contemporary satellite image-processing subjects is cloud and cloud shade segmentation. Due to substantial background noise interference, existing cloud and cloud shadow segmentation techniques would result in false detection and missing detection. We propose a Location Pooling Multi-Scale Network (LPMSNet) in this study. The residual network is utilised as the backbone in this method to acquire semantic info on various levels. Simultaneously, the Location Attention Multi-Scale Aggregation Module (LAMA) is introduced to obtain the image’s multi-scale info. The Channel Spatial Attention Module (CSA) is introduced to boost the network’s focus on segmentation goals. Finally, in view of the problem that the edge details of cloud as well as cloud shade are easily lost, this work designs the Scale Fusion Restoration Module (SFR). SFR can perform picture upsampling as well as the acquisition of edge detail information from cloud as well as cloud shade. The mean intersection over union (MIoU) accuracy of this network reached 94.36% and 81.60% on the Cloud and Cloud Shadow Dataset and the five-category dataset L8SPARCS, respectively. On the two-category HRC-WHU Dataset, the accuracy of the network on the intersection over union (IoU) reached 90.51%. In addition, in the Cloud and Cloud Shadow Dataset, our network achieves 97.17%, 96.83%, and 97.00% in precision (P), recall (R), and F1 score (F1) in cloud segmentation tasks, respectively. In the cloud shadow segmentation task, precision (P), recall (R), and F1 score (F1) reached 95.70%, 96.38%, and 96.04%, respectively. Therefore, this method has a significant advantage over the current cloud and cloud shade segmentation methods.

DSA-Net: Infrared and Visible Image Fusion via Dual-Stream Asymmetric Network.

Infrared and visible image fusion technologies are used to characterize the same scene using diverse modalities. However, most existing deep learning-based fusion methods are designed as symmetric networks, which ignore the differences between modal images and lead to source image information loss during feature extraction. In this paper, we propose a new fusion framework for the different characteristics of infrared and visible images. Specifically, we design a dual-stream asymmetric network with two different feature extraction networks to extract infrared and visible feature maps, respectively. The transformer architecture is introduced in the infrared feature extraction branch, which can force the network to focus on the local features of infrared images while still obtaining their contextual information. The visible feature extraction branch uses residual dense blocks to fully extract the rich background and texture detail information of visible images. In this way, it can provide better infrared targets and visible details for the fused image. Experimental results on multiple datasets indicate that DSA-Net outperforms state-of-the-art methods in both qualitative and quantitative evaluations. In addition, we also apply the fusion results to the target detection task, which indirectly demonstrates the fusion performances of our method.

Towards Compact Single Image Dehazing via Task-related Contrastive Network

Single image dehazing is a challenging vision task that recovers haze-free images from observed hazy images. Recently, numerous learning-based dehazing methods have been proposed and achieved promising performance. However, most of them suffer from a heavy computation burden, and even worse, they cannot leverage negative-orient supervision information well in the training stage. To address the above issues, we propose a novel dehazing method called Task-related Contrastive Network (TC-Net). For a better trade-off between performance and parameters, we design a compact dehazing network based on autoencoder-like architecture. It mainly includes two key modules: the feature enhanced module and the attention fusion module, which can improve the feature representation capability of the network and preserve details information, respectively. More importantly, we propose a task-related contrastive learning framework to fully exploit the negative-orient supervision information. To be specific, we utilize various task-specific data augmentation approaches (e.g., blur, sharpening, color, and light enhancement) to generate informative positive samples and hard negative samples, respectively. Furthermore, we employ an efficient and task-friendly feature embedding network, i.e., the encoder of the dehazing pipeline instead of the pre-trained model, to encode augmented samples into the latent space where negative-orient supervision information can be fully leveraged by contrastive constraint. Extensive experiments demonstrate that our TC-Net can obtain remarkable performance compared with other state-of-the-art dehazing methods, by extreme PSNR gains of 1.75 dB and 0.52 dB, on SOTS and Dense-Haze datasets, respectively.

TMSDNet: Transformer with multi‐scale dense network for single and multi‐view 3D reconstruction

Abstract3D reconstruction is a long‐standing problem. Recently, a number of studies have emerged that utilize transformers for 3D reconstruction, and these approaches have demonstrated strong performance. However, transformer‐based 3D reconstruction methods tend to establish the transformation relationship between the 2D image and the 3D voxel space directly using transformers or rely solely on the powerful feature extraction capabilities of transformers. They ignore the crucial role played by deep multi‐scale representation of the object in the voxel feature domain, which can provide extensive global shape and local detail information about the object in a multi‐scale manner. In this article, we propose a novel framework TMSDNet (transformer with multi‐scale dense network) for single‐view and multi‐view 3D reconstruction with transformer to solve this problem. Based on our well‐designed combined‐transformer Block, which is canonical encoder–decoder architecture, voxel features with spatial order can be extracted from the input image, which are used to further extract multi‐scale global features in parallel using a multi‐scale residual attention module. Furthermore, a residual dense attention block is introduced for deep local features extraction and adaptive fusion. Finally, the reconstructed objects are produced with the voxel reconstruction block. Experiment results on the benchmarks such as ShapeNet and Pix3D datasets demonstrate that TMSDNet outperforms the existing state‐of‐the‐art reconstruction methods substantially.

FPIseg: Iterative segmentation network based on feature pyramid for few‐shot segmentation

AbstractFew‐shot segmentation (FSS) enables rapid adaptation to the segmentation task of unseen‐classes object based on a few labelled support samples. Currently, the focal point of research in the FSS field is to align features between support and query images, aiming to improve the segmentation performance. However, most existing FSS methods implement such support/query alignment by solely leveraging middle‐level feature for generalization, ignoring the category semantic information contained in high‐level feature, while pooling operation inevitably lose spatial information of the feature. To alleviate these issues, the authors propose the Iterative Segmentation Network Based on Feature Pyramid (FPIseg), which mainly consists of three modules: Feature Pyramid Fusion Module (FPFM), Region Feature Enhancement Module (RFEM), and Iterative Optimization Segmentation Module (IOSM). Firstly, FPFM fully utilizes the foreground information from the support image to implement support/query alignment under multi‐scale, multi‐level semantic backgrounds. Secondly, RFEM enhances the foreground detail information of aligned feature to improve generalization ability. Finally, ISOM iteratively segments the query image to optimize the prediction result and improve segmentation performance. Extensive experiments on the PASCAL‐5i and COCO‐20i datasets show that FPIseg achieves considerable segmentation performance under both 1‐shot and 5‐shot settings.