Complex & Intelligent Systems最新文献

{"title":"A novel graph convolution and frequency domain filtering approach for hyperspectral anomaly detection","authors":"Yang Ding, Hao Yan, Jingyuan He, Juanjuan Yin, A. Ruhan","doi":"10.1007/s40747-024-01738-z","DOIUrl":"https://doi.org/10.1007/s40747-024-01738-z","url":null,"abstract":"<p>This paper introduces a novel algorithm for hyperspectral anomaly detection (HAD) that combines graph-based representations with frequency domain filtering techniques. In this approach, hyperspectral images (HSIs) are modeled as graphs, where each pixel is treated as a node with spectral features, and the edges capture pixel correlations based on the K-Nearest Neighbor (KNN) algorithm. Graph convolution is employed to extract spatial structural features, enhancing the understanding of spatial relationships within the data. Additionally, the algorithm addresses the ’right-shift’ phenomenon in the spectral domain, often associated with anomalies, by using a beta wavelet filter for efficient spectral filtering and anomaly detection. The key contributions of this work include: 1) the use of a graph-based model for HSI that effectively integrates both spatial and spectral dimensions, 2) employing KNN for edge construction to include distant pixels and mitigate noise, 3) spatial feature extraction via graph convolution to provide detailed insights into spatial interconnections and variations, enhancing the detection process, and 4) leveraging the beta wavelet filter to handle the ’right-shift’ spectral phenomenon and reduce computational complexity. Experimental evaluations on four benchmark datasets show that the proposed method achieves outstanding performance with AUC scores of 0.9986, 0.9975, 0.9859, and 0.9988, significantly outperforming traditional and state-of-the-art anomaly detection techniques.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"73 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142924656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CSTrans: cross-subdomain transformer for unsupervised domain adaptation","authors":"Junchi Liu, Xiang Zhang, Zhigang Luo","doi":"10.1007/s40747-024-01709-4","DOIUrl":"https://doi.org/10.1007/s40747-024-01709-4","url":null,"abstract":"<p>Unsupervised domain adaptation (UDA) aims to make full use of a labeled source domain data to classify an unlabeled target domain data. With the success of Transformer in various vision tasks, existing UDA methods borrow strong Transformer framework to learn global domain-invariant feature representation from the domain level or category level. Of them, the cross-attention as a key component acts for the cross-domain feature alignment, benefiting from its robustness. Intriguingly, we find that the robustness makes the model insensitive to the sub-grouping property within the same category of both source and target domains, known as the subdomain structure. This is because the robustness regards some fine-grained information as the noises and removes them. To overcome this shortcoming, we propose an end-to-end Cross-Subdomain Transformer framework (CSTrans) to exploit the transferability of subdomain structures and the robustness of cross-attention to calibrate inter-domain features. Specifically, there are two innovations in this paper. First, we devise an efficient Index Matching Module (IMM) to calculate the cross-attention of the same category in different domains and learn the domain-invariant representation. This not only simplifies the traditional daunting image-pair selection but also paves the safer way for guarding fine-grained subdomain information. This is because the IMM implements reliable feature confusion. Second, we introduce discriminative clustering to mine the subdomain structures in the same category and further learn subdomain discrimination. Both aspects cooperates with each other for fewer training stages. We perform extensive studies on five benchmarks, and the respective experimental results show that, as compared to existing UDA siblings, CSTrans attains remarkable results with average classification accuracy of 94.3%, 92.1%, and 85.4% on datasets Office-31, ImageCLEF-DA, and Office-Home, respectively.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"28 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142924739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IMTLM-Net: improved multi-task transformer based on localization mechanism network for handwritten English text recognition","authors":"Qianfeng Zhang, Feng Liu, Wanru Song","doi":"10.1007/s40747-024-01713-8","DOIUrl":"https://doi.org/10.1007/s40747-024-01713-8","url":null,"abstract":"<p>Intelligence technology has widely empowered education. As an example, Optical Character Recognition (OCR) can be used in smart education scenarios such as online homework correction and teaching data analysis. One of the fundamental yet challenging tasks is to recognize images of handwritten English text as editable text accurately. This is because handwritten text tends to have different writing habits as well as smearing and overlapping, resulting in hard alignment between the image and the real text. Additionally, the lack of data on handwritten text further leads to a lower recognition rate. To address the above issue, on the one hand, this paper extends the existing dataset and introduces hyphenated data annotation to provide data support for improving the robustness and discrimination of the model; on the other hand, a novel framework named Improved Multi-task Transformer based on Localization Mechanism Network (IMTLM-Net) is proposed for handwritten English text recognition. IMTLM-Net contains two parts, namely the encoding and decoding modules. The encoding module introduces a dual-stream processing mechanism. That is, in the simultaneous processing of text and images, a Vision Transformer (VIT) is utilized to encode images, and a Permutation Language Model (PLM) is designed for word arrangement. Two Multiple Head Attention (MHA) units are employed in the decoding module, focusing on text sequences and image sequences. Moreover, the localization mechanism (LM) is applied to enhance font structure feature extraction from image data, which in turn improves the model’s ability to capture complex details. Numerous experiments demonstrate that the proposed method achieves state-of-the-art results in handwritten text recognition.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"5 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142924737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Graph attention, learning 2-opt algorithm for the traveling salesman problem","authors":"Jia Luo, Herui Heng, Geng Wu","doi":"10.1007/s40747-024-01716-5","DOIUrl":"https://doi.org/10.1007/s40747-024-01716-5","url":null,"abstract":"<p>In recent years, deep graph neural networks (GNNs) have been used as solvers or helper functions for the traveling salesman problem (TSP), but they are usually used as encoders to generate static node representations for downstream tasks and are incapable of obtaining the dynamic permutational information in completely updating solutions. For addressing this problem, we propose a permutational encoding graph attention encoder and attention-based decoder (PEG2A) model for the TSP that is trained by the advantage actor-critic algorithm. In this work, the permutational encoding graph attention (PEGAT) network is designed to encode node embeddings for gathering information from neighbors and obtaining the dynamic graph permutational information simultaneously. The attention-based decoder is tailored to compute probability distributions over picking pair nodes for 2-opt moves. The experimental results show that our method outperforms the compared learning-based algorithms and traditional heuristic methods.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"17 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142917071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel transmission-augmented deep unfolding network with consideration of residual recovery","authors":"Zhijie Zhang, Huang Bai, Ljubiša Stanković, Junmei Sun, Xiumei Li","doi":"10.1007/s40747-024-01727-2","DOIUrl":"https://doi.org/10.1007/s40747-024-01727-2","url":null,"abstract":"<p>Compressive sensing (CS) has been widely applied in signal processing field, especially for image reconstruction tasks. CS simplifies the sampling and compression procedures, but leaves the difficulty to the nonlinear reconstruction. Traditional CS reconstruction algorithms are usually iterative, having a complete theoretical foundation. Nevertheless, these iterative algorithms suffer from the high computational complexity. The fashionable deep network-based methods can achieve high-precision CS reconstruction with satisfactory speed but are short of theoretical analysis and interpretability. To combine the merits of the above two kinds of CS methods, the deep unfolding networks (DUNs) have been developed. In this paper, a novel DUN named supervised transmission-augmented network (SuperTA-Net) is proposed. Based on the framework of our previous work PIPO-Net, the multi-channel transmission strategy is put forward to reduce the influence of critical information loss between modules and improve the reliability of data. Besides, in order to avoid the issues such as high information redundancy and high computational burden when too many channels are set, the attention based supervision scheme is presented to dynamically adjust the weight of each channel and remove the redundant information. Furthermore, noting the difference between the original image and the output of SuperTA-Net, the reinforcement network is developed, where the main component called residual recovery network (RR-Net) is lightweight and can be added to reinforce all kinds of CS reconstruction networks. Experiments on reconstructing CS images demonstrate the effectiveness of the proposed networks.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"55 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142917324","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PLZero: placeholder based approach to generalized zero-shot learning for multi-label recognition in chest radiographs","authors":"Chengrong Yang, Qiwen Jin, Fei Du, Jing Guo, Yujue Zhou","doi":"10.1007/s40747-024-01717-4","DOIUrl":"https://doi.org/10.1007/s40747-024-01717-4","url":null,"abstract":"<p>By leveraging large-scale image-text paired data for pre-training, the model can efficiently learn the alignment between images and text, significantly advancing the development of zero-shot learning (ZSL) in the field of intelligent medical image analysis. However, the heterogeneity between cross-modalities, false negatives in image-text pairs, and domain shift phenomena pose challenges, making it difficult for existing methods to effectively learn the deep semantic relationships between images and text. To address these challenges, we propose a multi-label chest X-ray recognition generalized ZSL framework based on placeholder learning, termed PLZero. Specifically, we first introduce a jointed embedding space learning module (JESL) to encourage the model to better capture the diversity among different labels. Secondly, we propose a hallucinated class generation module (HCG), which generates hallucinated classes by feature diffusion and feature fusion based on the visual and semantic features of seen classes, using these hallucinated classes as placeholders for unseen classes. Finally, we propose a hallucinated class-based prototype learning module (HCPL), which leverages contrastive learning to control the distribution of hallucinated classes around seen classes without significant deviation from the original data, encouraging high dispersion of class prototypes for seen classes to create sufficient space for inserting unseen class samples. Extensive experiments demonstrate that our method exhibits sufficient generalization and achieves the best performance across three classic and challenging chest X-ray datasets: NIH Chest X-ray 14, CheXpert, and ChestX-Det10. Notably, our method outperforms others even when the number of unseen classes exceeds the experimental settings of other methods. The codes are available at: https://github.com/jinqiwen/PLZero.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"27 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142917069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MSM-TDE: multi-scale semantics mining and tiny details enhancement network for retinal vessel segmentation","authors":"Hongbin Zhang, Jin Zhang, Xuan Zhong, Ya Feng, Guangli Li, Xiong Li, Jingqin Lv, Donghong Ji","doi":"10.1007/s40747-024-01714-7","DOIUrl":"https://doi.org/10.1007/s40747-024-01714-7","url":null,"abstract":"<p>Retinal image segmentation is crucial for the early diagnosis of some diseases like diabetes and hypertension. Current methods face many challenges, such as inadequate multi-scale semantics and insufficient global information. In view of this, we propose a network called multi-scale semantics mining and tiny details enhancement (MSM-TDE). First, a multi-scale feature input module is designed to capture multi-scale semantics information from the source. Then a fresh multi-scale attention guidance module is constructed to mine local multi-scale semantics while a global semantics enhancement module is proposed to extract global multi-scale semantics. Additionally, an auxiliary vessel detail enhancement branch using dynamic snake convolution is built to enhance the tiny vessel details. Extensive experimental results on four public datasets validate the superiority of MSM-TDE, which obtains competitive performance with satisfactory model complexity. Notably, this study provides an innovative idea of multi-scale semantics mining by diverse methods.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"70 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142917068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"APDL: an adaptive step size method for white-box adversarial attacks","authors":"Jiale Hu, Xiang Li, Changzheng Liu, Ronghua Zhang, Junwei Tang, Yi Sun, Yuedong Wang","doi":"10.1007/s40747-024-01748-x","DOIUrl":"https://doi.org/10.1007/s40747-024-01748-x","url":null,"abstract":"<p>Recent research has shown that deep learning models are vulnerable to adversarial attacks, including gradient attacks, which can lead to incorrect outputs. The existing gradient attack methods typically rely on repetitive multistep strategies to improve their attack success rates, resulting in longer training times and severe overfitting. To address these issues, we propose an adaptive perturbation-based gradient attack method with dual-loss optimization (APDL). This method adaptively adjusts the single-step perturbation magnitude based on an exponential distance function, thereby accelerating the convergence process. APDL achieves convergence in fewer than 10 iterations, outperforming the traditional nonadaptive methods and achieving a high attack success rate with fewer iterations. Furthermore, to increase the transferability of gradient attacks such as APDL across different models and reduce the effects of overfitting on the training model, we introduce a triple-differential logit fusion (TDLF) method grounded in knowledge distillation principles. This approach mitigates the edge effects associated with gradient attacks by adjusting the hardness and softness of labels. Experiments conducted on ImageNet-compatible datasets demonstrate that APDL is significantly faster than the commonly used nonadaptive methods, whereas the TDLF method exhibits strong transferability.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"34 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142917070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MM-HiFuse: multi-modal multi-task hierarchical feature fusion for esophagus cancer staging and differentiation classification","authors":"Xiangzuo Huo, Shengwei Tian, Long Yu, Wendong Zhang, Aolun Li, Qimeng Yang, Jinmiao Song","doi":"10.1007/s40747-024-01708-5","DOIUrl":"https://doi.org/10.1007/s40747-024-01708-5","url":null,"abstract":"<p>Esophageal cancer is a globally significant but understudied type of cancer with high mortality rates. The staging and differentiation of esophageal cancer are crucial factors in determining the prognosis and surgical treatment plan for patients, as well as improving their chances of survival. Endoscopy and histopathological examination are considered as the gold standard for esophageal cancer diagnosis. However, some previous studies have employed deep learning-based methods for esophageal cancer analysis, which are limited to single-modal features, resulting in inadequate classification results. In response to these limitations, multi-modal learning has emerged as a promising alternative for medical image analysis tasks. In this paper, we propose a hierarchical feature fusion network, MM-HiFuse, for multi-modal multitask learning to improve the classification accuracy of esophageal cancer staging and differentiation level. The proposed architecture combines low-level to deep-level features of both pathological and endoscopic images to achieve accurate classification results. The key characteristics of MM-HiFuse include: (i) a parallel hierarchy of convolution and self-attention layers specifically designed for pathological and endoscopic image features; (ii) a multi-modal hierarchical feature fusion module (MHF) and a new multitask weighted combination loss function. The benefits of these features are the effective extraction of multi-modal representations at different semantic scales and the mutual complementarity of the multitask learning, leading to improved classification performance. Experimental results demonstrate that MM-HiFuse outperforms single-modal methods in esophageal cancer staging and differentiation classification. Our findings provide evidence for the early diagnosis and accurate staging of esophageal cancer and serve as a new inspiration for the application of multi-modal multitask learning in medical image analysis. Code is available at https://github.com/huoxiangzuo/MM-HiFuse.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"67 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implicit link prediction based on extended social graph","authors":"Ling Xing, Jinxin Liu, Qi Zhang, Honghai Wu, Huahong Ma, Xiaohui Zhang","doi":"10.1007/s40747-024-01736-1","DOIUrl":"https://doi.org/10.1007/s40747-024-01736-1","url":null,"abstract":"<p>Link prediction infers the likelihood of a connection between two nodes based on network structural information, aiming to foresee potential latent relationships within the network. In social networks, nodes typically represent users, and links denote the relationships between users. However, some user nodes in social networks are hidden due to unknown or incomplete link information. The prediction of implicit links between these nodes and other user nodes is hampered by incomplete network structures and partial node information, affecting the accuracy of link prediction. To address these issues, this paper introduces an implicit link prediction algorithm based on extended social graph (ILP-ESG). The algorithm completes user attribute information through a multi-task fusion attribute inference framework built on associative learning. Subsequently, an extended social graph is constructed based on user attribute relations, social relations, and discourse interaction relations, enriching user nodes with comprehensive representational information. A semi-supervised graph autoencoder is then employed to extract features from the three types of relationships in the extended social graph, obtaining feature vectors that effectively represent the multidimensional relationship information of users. This facilitates the inference of potential implicit links between nodes and the prediction of hidden user relationships with others. This algorithm is validated on real datasets, and the results show that under the Facebook dataset, the algorithm improves the AUC and Precision metrics by an average of 5.17<span>(%)</span> and 9.25<span>(%)</span> compared to the baseline method, and under the Instagram dataset, it improves by 7.71<span>(%)</span> and 16.16<span>(%)</span>, respectively. Good stability and robustness are exhibited, ensuring the accuracy of link prediction.</p>","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"178 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142905456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}