Search Results (529)

A near-real-time change detection network can consistently identify unauthorized construction activities over a wide area, empowering authorities to enforce regulations efficiently. Furthermore, it can promptly assess building damage, enabling expedited rescue efforts. The extensive adoption of deep learning in change detection has prompted a predominant emphasis on enhancing detection performance, primarily through the expansion of the depth and width of networks, overlooking considerations regarding inference time and computational cost. To accurately represent the spatio-temporal semantic correlations between pre-change and post-change images, we create an innovative transformer attention mechanism named Sliding-Window Dissimilarity Cross-Attention (SWDCA), which detects spatio-temporal semantic discrepancies by explicitly modeling the dissimilarity of bi-temporal tokens, departing from the mono-temporal similarity attention typically used in conventional transformers. In order to fulfill the near-real-time requirement, SWDCA employs a sliding-window scheme to limit the range of the cross-attention mechanism within a predetermined window/dilated window size. This approach not only excludes distant and irrelevant information but also reduces computational cost. Furthermore, we develop a lightweight Siamese backbone for extracting building and environmental features. Subsequently, we integrate an SWDCA module into this backbone, forming an efficient change detection network. Quantitative evaluations and visual analyses of thorough experiments verify that our method achieves top-tier accuracy on two building change detection datasets of remote sensing imagery, while also achieving a real-time inference speed of 33.2 FPS on a mobile GPU. Full article

This paper addresses the challenges of low accuracy and long transfer learning time in small-sample bearing fault diagnosis, which are often caused by limited samples, high noise levels, and poor feature extraction. We propose a method that combines an improved capsule network with a Siamese neural network. Multi-view data partitioning is used to enrich data diversity, and Markov transformation converts one-dimensional vibration signals into two-dimensional images, enhancing the visualization of signal features. The dynamic routing mechanism of the capsule network effectively captures and integrates key fault features, improving the model’s feature representation and robustness. The Siamese network shares weights to optimize feature matching, while SKNet dynamically adjusts feature fusion to enhance generalization performance. By integrating the Siamese neural network with SKNet, we improve transfer efficiency, reduce the number of parameters, and lighten the model to reduce complexity and shorten transfer time. Experimental results demonstrate that this method can accurately identify faults under conditions of limited samples and high noise, thereby improving diagnostic accuracy and reducing transfer time. Full article

The fuel system serves as the core component of marine diesel engines, and timely and effective fault diagnosis is the prerequisite for the safe navigation of ships. To address the challenge of current data-driven fault-diagnosis-based methods, which have difficulty in feature extraction and low accuracy under small samples, this paper proposes a fault diagnosis method based on digital twin (DT), Siamese Vision Transformer (SViT), and K-Nearest Neighbor (KNN). Firstly, a diesel engine DT model is constructed by integrating the mathematical, mechanism, and three-dimensional physical models of the Medium-speed diesel engines of 6L21/31 Marine, completing the mapping from physical entity to virtual entity. Fault simulation calculations are performed using the DT model to obtain different types of fault data. Then, a feature extraction network combining Siamese networks with Vision Transformer (ViT) is proposed for the simulated samples. An improved KNN classifier based on the attention mechanism is added to the network to enhance the classification efficiency of the model. Meanwhile, a Weighted-Similarity loss function is designed using similarity labels and penalty coefficients, enhancing the model’s ability to discriminate between similar sample pairs. Finally, the proposed method is validated using a simulation dataset. Experimental results indicate that the proposed method achieves average accuracies of 97.22%, 98.21%, and 99.13% for training sets with 10, 20, and 30 samples per class, respectively, which can accurately classify the fault of marine fuel systems under small samples and has promising potential for applications. Full article

Despite the accuracy and robustness attained in the field of object tracking, algorithms based on Siamese neural networks often over-rely on information from the initial frame, neglecting necessary updates to the template; furthermore, in prolonged tracking situations, such methodologies encounter challenges in efficiently addressing issues such as complete occlusion or instances where the target exits the frame. To tackle these issues, this study enhances the SiamRPN algorithm by integrating the convolutional block attention module (CBAM), which enhances spatial channel attention. Additionally, it integrates the kernelized correlation filters (KCFs) for enhanced feature template representation. Building on this, we present DSiam-CnK, a Siamese neural network with dynamic template updating capabilities, facilitating adaptive adjustments in tracking strategy. The proposed algorithm is tailored to elevate the Siamese neural network’s accuracy and robustness for prolonged tracking, all the while preserving its tracking velocity. In our research, we assessed the performance on the OTB2015, VOT2018, and LaSOT datasets. Our method, when benchmarked against established trackers, including SiamRPN on OTB2015, achieved a success rate of 92.1% and a precision rate of 90.9%. On the VOT2018 dataset, it excelled, with a VOT-A (accuracy) of 46.7%, a VOT-R (robustness) of 135.3%, and a VOT-EAO (expected average overlap) of 26.4%, leading in all categories. On the LaSOT dataset, it achieved a precision of 35.3%, a normalized precision of 34.4%, and a success rate of 39%. The findings demonstrate enhanced precision in tracking performance and a notable increase in robustness with our method. Full article

With the development of unmanned aerial vehicle (UAV) technology, the threat of UAV intrusion is no longer negligible. Therefore, drone perception, especially anti-UAV tracking technology, has gathered considerable attention. However, both traditional Siamese and transformer-based trackers struggle in anti-UAV tasks due to the small target size, clutter backgrounds and model degradation. To alleviate these challenges, a novel contrastive-augmented memory network (CAMTracker) is proposed for anti-UAV tracking tasks in thermal infrared (TIR) videos. The proposed CAMTracker conducts tracking through a two-stage scheme, searching for possible candidates in the first stage and matching the candidates with the template for final prediction. In the first stage, an instance-guided region proposal network (IG-RPN) is employed to calculate the correlation features between the templates and the searching images and further generate candidate proposals. In the second stage, a contrastive-augmented matching module (CAM), along with a refined contrastive loss function, is designed to enhance the discrimination ability of the tracker under the instruction of contrastive learning strategy. Moreover, to avoid model degradation, an adaptive dynamic memory module (ADM) is proposed to maintain a dynamic template to cope with the feature variation of the target in long sequences. Comprehensive experiments have been conducted on the Anti-UAV410 dataset, where the proposed CAMTracker achieves the best performance compared to advanced tracking algorithms, with significant advantages on all the evaluation metrics, including at least 2.40%, 4.12%, 5.43% and 5.48% on precision, success rate, success AUC and state accuracy, respectively. Full article

Recent advancements in the field of object tracking have been notably influenced by Siamese-based trackers, which have demonstrated considerable progress in their performance and application. Researchers frequently emphasize the precision of trackers, yet they tend to neglect the associated complexity. This oversight can restrict real-time performance, rendering these trackers inadequate for specific applications. This study presents a novel lightweight Siamese network tracker, termed SiamGCN, which incorporates global feature fusion alongside a lightweight network architecture to improve tracking performance on devices with limited resources. MobileNet-V3 was chosen as the backbone network for feature extraction, with modifications made to the stride of its final layer to enhance extraction efficiency. A global correlation module, which was founded on the Transformer architecture, was developed utilizing a multi-head cross-attention mechanism. This design enhances the integration of template and search region features, thereby facilitating more precise and resilient tracking capabilities. The model underwent evaluation across four prominent tracking benchmarks: VOT2018, VOT2019, LaSOT, and TrackingNet. The results indicate that SiamGCN achieves high tracking performance while simultaneously decreasing the number of parameters and computational costs. This results in significant benefits regarding processing speed and resource utilization. Full article

In tasks such as wood defect repair and the production of high-end wooden furniture, ensuring the consistency of the texture in repaired or jointed areas is crucial. This paper proposes the WTSM-SiameseNet model for wood-texture-similarity matching and introduces several improvements to address the issues present in traditional methods. First, to address the issue that fixed receptive fields cannot adapt to textures of different sizes, a multi-receptive field fusion feature extraction network was designed. This allows the model to autonomously select the optimal receptive field, enhancing its flexibility and accuracy when handling wood textures at different scales. Secondly, the interdependencies between layers in traditional serial attention mechanisms limit performance. To address this, a concurrent attention mechanism was designed, which reduces interlayer interference by using a dual-stream parallel structure that enhances the ability to capture features. Furthermore, to overcome the issues of existing feature fusion methods that disrupt spatial structure and lack interpretability, this study proposes a feature fusion method based on feature correlation. This approach not only preserves the spatial structure of texture features but also improves the interpretability and stability of the fused features and the model. Finally, by introducing depthwise separable convolutions, the issue of a large number of model parameters is addressed, significantly improving training efficiency while maintaining model performance. Experiments were conducted using a wood texture similarity dataset consisting of 7588 image pairs. The results show that WTSM-SiameseNet achieved an accuracy of 96.67% on the test set, representing a 12.91% improvement in accuracy and a 14.21% improvement in precision compared to the pre-improved SiameseNet. Compared to CS-SiameseNet, accuracy increased by 2.86%, and precision improved by 6.58%. Full article

Lymphoma is the most common haematopoietic cancer in cats with few large studies evaluating breed and sex as risk factors for the disease. Australia’s geographic isolation and quarantine rules have led to a potentially restricted genetic pool and, currently, there have not been any large local epidemiological studies reported. A total of 1705 lymphoma cases were identified from several sources and compared to a reference population of 85,741 cats, and represent cats that are presented to veterinary clinics. Odds ratios were calculated for each breed that included lymphoma cases, as well as sex, retroviral status, and immunophenotype. The distributions of age and weight in the lymphoma and control populations and proportions of lymphoma cases in anatomic locations were compared. Eight breeds were identified as displaying increased potential risk of lymphoma and three at decreased risk. Male cats were found to be at increased risk (OR 1.2, 95%CI: 1.1 to 1.3, p = 0.002). The lymphoma cases were older, with a median age of 11.7 years compared to 9.0 years (p < 0.0001), and weighed less, with a median weight of 3.7 kg compared to 4.0 kg (p = 0.010), than the control population. Several breeds were found to have significant variations in the proportions of anatomical presentations including the Siamese, Burmilla, Australian mist, ragdoll, British shorthair, and domestic cats. These findings require confirmation in future studies that address the limitations of this study, as outlined in the discussion. Full article

The surface texture of objects in industrial scenes is complex and diverse, and the characteristics of surface defects are often very similar to the surrounding environment and texture background, so it is difficult to accurately detect the defect area. However, when deep learning technology is used to detect complex texture surface defects, the detection accuracy is not high, due to the lack of large-scale pixel-level label datasets. Therefore, a defect detection model Siamese-RCNet for complex texture surface with a small number of annotations is proposed. The Cascade R-CNN target detection network is used as the basic framework, making full use of unlabeled image feature information, and fusing the nonlinear relationship learning ability of Siamese network and the feature extraction ability of the Res2Net backbone network to more effectively capture the subtle features of complex texture surface defects. The image difference measurement method is used to calculate the similarity between different images, and the attention module is constructed to weight the feature map of the feature extraction pyramid, so that the model can focus more on the defect area and suppress the influence of complex background texture area, so as to improve the accuracy of detection. To verify the effectiveness of the Siamese-RCNet model, a series of experiments were carried out on the DAGM2007 dataset of weakly supervised learning texture surface defects for industrial optical inspection. The results show that even if only 20% of the labeled datasets are used, the [email protected] of the Siamese-RCNet model can still reach 96.9%. Compared with the traditional Cascade R-CNN and Faster R-CNN target detection networks, the Siamese-RCNet model has high accuracy, can reduce the workload of manual labeling, and provides strong support for practical applications. Full article

Survival analysis aims to analyze the relationship between covariates and events of interest, and is widely applied in multiple research fields, especially in clinical fields. Recently, some studies have attempted to discover potential sub-populations in survival data to assist in survival prediction with clustering. However, existing models that combine clustering with survival analysis face multiple challenges: incomplete representation caused by single-path encoders, the incomplete information of pseudo-samples, and misleading effects of boundary samples. To overcome these challenges, in this study, we propose a novel deep contrastive survival analysis model with dual-view clustering. Specifically, we design a Siamese autoencoder to construct latent spaces in two views and conduct dual-view clustering to more comprehensively capture patient representations. Moreover, we consider the dual views as mutual augmentations rather than introducing pseudo-samples and, based on this, triplet contrastive learning is proposed to fully utilize clustering information and dual-view representations to enhance survival prediction. Additionally, we employ a self-paced learning strategy in the dual-view clustering process to ensure the model handles samples from easy to hard in training, thereby avoiding the misleading effects of boundary samples. Our proposal achieves an average C-index and IBS of 0.6653 and 0.1786 on three widely used clinical datasets, both exceeding the existing best methods, which demonstrates its advanced discriminative and calibration performance. Full article

Pan-sharpening aims to generate high-resolution (HR) multispectral (MS) images by fusing HR panchromatic (PAN) and low-resolution (LR) MS images covering the same area. However, due to the lack of real HR MS reference images, how to accurately evaluate the quality of a fused image without reference is challenging. On the one hand, most methods evaluate the quality of the fused image using the full-reference indices based on the simulated experimental data on the popular Wald’s protocol; however, this remains controversial to the full-resolution data fusion. On the other hand, existing limited no reference methods, most of which depend on manually crafted features, cannot fully capture the sensitive spatial/spectral distortions of the fused image. Therefore, this paper proposes a perceptual quality assessment method based on deep feature similarity measure. The proposed network includes spatial/spectral feature extraction and similarity measure (FESM) branch and overall evaluation network. The Siamese FESM branch extracts the spatial and spectral deep features and calculates the similarity of the corresponding pair of deep features to obtain the spatial and spectral feature parameters, and then, the overall evaluation network realizes the overall quality assessment. Moreover, we propose to quantify both the overall precision of all the training samples and the variations among different fusion methods in a batch, thereby enhancing the network’s accuracy and robustness. The proposed method was trained and tested on a large subjective evaluation dataset comprising 13,620 fused images. The experimental results suggested the effectiveness and the competitive performance. Full article

Moving object detection (MOD) plays an important role in many applications that aim to identify regions of interest in videos. However, most existing MOD methods ignore the variability brought by time-varying information. Additionally, many network frameworks primarily focus on low-level feature learning, neglecting the higher-level contextual understanding required for accurate detection. To solve the above issues, we propose a symmetric Dynamic-Aware Network (DAN) for MOD. DAN explores the interactions between different types of information via structural design and feature optimization. To locate the object position quickly, we build a Siamese convolutional network to emphasize changes in the scene. Subsequently, a Change-Aware Module (CAM) is designed, which can maximize the perception of object change cues by exploiting complementary depth-varying features and different levels of disparity information, thereby enhancing the feature discrimination capability of the network. Moreover, to reinforce the effective transfer between features, we devise a Motion-Attentive Selection Module (MASM) to construct an autonomous decoder for augmenting detail representation. Experimental results on benchmark datasets indicate the rationality and validity of the proposed approach. Full article

Sleep apnea syndrome (SAS) affects about 3–7% of the global population, but is often undiagnosed. It involves pauses in breathing during sleep, for at least 10 s, due to partial or total airway blockage. The current gold standard for diagnosing SAS is polysomnography (PSG), an intrusive procedure that depends on subjective assessment by expert clinicians. To address the limitations of PSG, we propose a decision support system, which uses a tracheal microphone for data collection and a deep learning (DL) approach—namely SiCRNN—to detect apnea events during overnight sleep recordings. Our proposed SiCRNN processes Mel spectrograms using a Siamese approach, integrating a convolutional neural network (CNN) backbone and a bidirectional gated recurrent unit (GRU). The final detection of apnea events is performed using an unsupervised clustering algorithm, specifically k-means. Multiple experimental runs were carried out to determine the optimal network configuration and the most suitable type and frequency range for the input data. Tests with data from eight patients showed that our method can achieve a $Recall$ score of up to 95% for apnea events. We also compared the proposed approach to a fully convolutional baseline, recently introduced in the literature, highlighting the effectiveness of the Siamese training paradigm in improving the identification of SAS. Full article

Object tracking in remote sensing videos is a challenging task in computer vision. Recent advances in deep learning have sparked significant interest in tracking algorithms based on Siamese neural networks. However, many existing algorithms fail to deliver satisfactory performance in complex scenarios due to challenging conditions and limited computational resources. Thus, enhancing tracking efficiency and improving algorithm responsiveness in complex scenarios are crucial. To address tracking drift caused by similar objects and background interference in remote sensing image tracking, we propose an enhanced Siamese network based on the SiamRhic architecture, incorporating a cross-correlation and ranking head for improved object tracking. We first use convolutional neural networks for feature extraction and integrate the CBAM (Convolutional Block Attention Module) to enhance the tracker’s representational capacity, allowing it to focus more effectively on the objects. Additionally, we replace the original depth-wise cross-correlation operation with asymmetric convolution, enhancing both speed and performance. We also introduce a ranking loss to reduce the classification confidence of interference objects, addressing the mismatch between classification and regression. We validate the proposed algorithm through experiments on the OTB100, UAV123, and OOTB remote sensing datasets. Specifically, SiamRhic achieves success, normalized precision, and precision rates of 0.533, 0.786, and 0.812, respectively, on the OOTB benchmark. The OTB100 benchmark achieves a success rate of 0.670 and a precision rate of 0.892. Similarly, in the UAV123 benchmark, SiamRhic achieves a success rate of 0.621 and a precision rate of 0.823. These results demonstrate the algorithm’s high precision and success rates, highlighting its practical value. Full article

In this paper, a novel Siamese network-based lightweight framework is proposed for automatic tomato leaf disease recognition. This framework achieves the highest accuracy of 96.97% on the tomato subset obtained from the PlantVillage dataset and 95.48% on the Taiwan tomato leaf disease dataset. Experimental results further confirm that the proposed framework is effective with imbalanced and small data. The backbone network integrated with this framework is lightweight with approximately 2.9629 million trainable parameters, which is second to SqueezeNet and significantly lower than other lightweight deep networks. Automatic tomato disease recognition from leaf images is vital to avoid crop losses by applying control measures on time. Even though recent deep learning-based tomato disease recognition methods with classical training procedures showed promising recognition results, they demand large labeled data and involve expensive training. The traditional deep learning models proposed for tomato disease recognition also consume high memory and storage because of a high number of parameters. While lightweight networks overcome some of these issues to a certain extent, they continue to show low performance and struggle to handle imbalanced data. Full article