Dual Feature Research Articles

BDD-GAN: a brocade image generation method via dual discriminator and feature fusion

BDD-GAN: a brocade image generation method via dual discriminator and feature fusion

DeepAge: Harnessing Deep Neural Network for Epigenetic Age Estimation From DNA Methylation Data of Human Blood Samples

Accurate prediction of biological age from DNA methylation data is a critical endeavor in understanding the molecular mechanisms of aging and developing age-related disease interventions. Traditional epigenetic clocks rely on linear regression or basic machine learning models, which often fail to capture the complex, non-linear interactions within methylation data. This study introduces DeepAge, a novel deep learning framework utilizing Temporal Convolutional Networks (TCNs) to enhance the prediction of biological age from DNA methylation profiles using selected CpGs by a Dual-Correlation based apparoach. DeepAge leverages a sequence-based approach with dilated convolutions to effectively capture long-range dependencies between CpG sites, addressing the limitations of prior models by incorporating advanced network architectures including residual connections and dropout regularization. The dual correlation feature selection enhances our model's predictive capabilities by identifying the most age-relevant CpG sites. Our model outperforms existing epigenetic clocks across multiple datasets, offering significant improvements in accuracy and providing deeper insights into the epigenetic determinants of aging. The proposed method not only sets a new standard in age estimation but also highlights the potential of deep learning in biologically relevant feature extraction and interpretation, contributing to the broader field of computational biology and precision medicine.

Disentangled feature fusion network for lightweight image super-resolution

Recently, the quality of generated images in image super-resolution (SR) has significantly improved due to the widespread application of convolutional neural networks. Existing super-resolution methods often overlook the importance of network width and instead prioritize designing deeper network structures to improve performance. Deeper networks, however, demand greater computational resources and are more challenging to train, making them less suitable for devices with limited performance. To address this issue, we propose a novel method called the disentangled feature fusion network (DFFN). Specifically, we construct dual feature extraction streams (DFES) using the strategies of feature disentanglement and parameter sharing, which increase the network's width without increasing the number of parameters. To facilitate the interaction of information between the dual feature extraction streams, we design a feature interaction module (FIM) that separately enhances high and low-frequency features. Furthermore, a feature fusion module (FFM) is presented to efficiently fuse different levels of high and low-frequency feature information. The proposed DFFN integrates DFES, FIM, and FFM, which not only widens the network without increasing parameters but also minimizes the loss of crucial feature information. Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms other state-of-the-art lightweight super-resolution methods, achieving a superior balance between parameter quantity, reconstruction performance, and model complexity. The code is available at https://github.com/zhoujy-aust/DFFN.

Word recognition from Indian Sign Language in videos using dual feature descriptor and GMT-MASKRCNN recognition technique

Word recognition from Indian Sign Language in videos using dual feature descriptor and GMT-MASKRCNN recognition technique

Attention Induced Dual Convolutional-Capsule Network (AIDC-CN): A deep learning framework for motor imagery classification

In recent times, Electroencephalography (EEG)-based motor imagery (MI) decoding has garnered significant attention due to its extensive applicability in healthcare, including areas such as assistive robotics and rehabilitation engineering. Nevertheless, the decoding of EEG signals presents considerable challenges owing to their inherent complexity, non-stationary characteristics, and low signal-to-noise ratio. Notably, deep learning-based classifiers have emerged as a prominent focus for addressing the EEG signal decoding process. This study introduces a novel deep learning classifier named the Attention Induced Dual Convolutional-Capsule Network (AIDC-CN) with the specific aim of accurately categorizing various motor imagination class labels. To enhance the classifier’s performance, a dual feature extraction approach leveraging spectrogram and brain connectivity networks has been employed, diversifying the feature set in the classification task. The main highlights of the proposed AIDC-CN classifier includes the introduction of a dual convolution layer to handle the brain connectivity and spectrogram features, addition of a novel self-attention module (SAM) to accentuate the relevant parts of the convolved spectrogram features, introduction of a new cross-attention module (CAM) to refine the outputs obtained from the dual convolution layers and incorporation of a Gaussian Error Linear Unit (GELU) based dynamic routing algorithm to strengthen the coupling among the primary and secondary capsule layers. Performance analysis undertaken on four public data sets depict the superior performance of the proposed model with respect to the state-of-the-art techniques. The code for this model is available at https://github.com/RiteshSurChowdhury/AIDC-CN.

Visual tracking algorithm based on template updating and dual feature enhancement

Aiming at the problem of tracking failure due to target deformation, flipping and occlusion in visual tracking, a template updating algorithm based on image structural similarity is proposed by dynamically updating the template to adapt to the changes of the target during tracking, specifically, a queue is used to save the recent N -frame tracking results, and a decision is made on whether to update the template or not based on the structural similarity score between the current tracking results and the template image, and if updated, the template is matched from the historical N -frame tracking results as the new template. If updated, the optimal target image is matched from the historical N -frame tracking results as a new template for subsequent tracking. The tracking feature enhancement module and segmentation feature enhancement module are also designed based on SiamMask network. The tracking feature enhancement module consists of non-local operations and convolutional downsampling, which is used to establish contextual correlation, enhance the target features, suppress the background interference, improve the tracking robustness, and solve the feature attenuation problem due to the occlusion of the target. The segmentation feature enhancement module introduces the convolutional block attention module and deformable convolution to improve the network's ability to capture channel and spatial features, adaptively learn the shape and contour information of the target, and enhance the network's segmentation accuracy of the tracked target. , which in turn improves the tracking accuracy. Experiments show that the proposed algorithm performs well and stably in solving the above problems, improving the expected average overlap rate by 5.2%, 5.3%, and 2.5%, and the robustness by 6%, 7.9%, and 15.6%on the VOT2016, VOT2018, and VOT2019 datasets , respectively, and achieving a real-time speed of 91 frames per second, when compared to the baseline SiamMask.

DPF-YOLOv8: Dual Path Feature Fusion Network for Traffic Sign Detection in Hazy Weather

Traffic sign detection plays an integral role in intelligent driving systems. It was found that in real driving scenarios, traffic signs were easily obscured by haze leading to traffic sign detection inaccuracy in assisted driving systems. Therefore, we designed a traffic sign detection model for hazy weather that can effectively help drivers to recognize road signs and reduce the incidence of traffic accidents. A high-precision traffic sign detection network has been designed to address the problem of decreased model recognition performance caused by external factors such as small size of traffic signs and haze obstruction in real-world scenarios. First, the default YOLOv8 was found to have low model detection accuracy in hazy weather occlusion conditions through experimental studies. Therefore, a deeper lightweight and efficient multi-branch CSP (Cross Stage Partial) module was introduced. Second, a dual path feature fusion network was designed to address the problem of insufficient feature fusion due to the small size of traffic signs. Finally, in order to be able to better simulate the real haze weather scene, we added fog to the raw data to enrich the data samples. This was verified through experiments on a public Chinese traffic sign detection dataset after fogging treatment, compared to the default YOLOv8 model. The improved DPF-YOLOv8 algorithm achieved 2.1% and 2.2% improvement in mAP@0.5 and mAP@0.5:0.95 performance metrics to 65.0% and 47.4%, respectively.

DAFE-MSGAT: Dual-Attention Feature Extraction and Multi-Scale Graph Attention Network for Polyphonic Piano Transcription

Automatic music transcription (AMT) aims to convert raw audio signals into symbolic music. This is a highly challenging task in the fields of signal processing and artificial intelligence, and it holds significant application value in music information retrieval (MIR). Existing methods based on convolutional neural networks (CNNs) often fall short in capturing the time-frequency characteristics of audio signals and tend to overlook the interdependencies between notes when processing polyphonic piano with multiple simultaneous notes. To address these issues, we propose a dual attention feature extraction and multi-scale graph attention network (DAFE-MSGAT). Specifically, we design a dual attention feature extraction module (DAFE) to enhance the frequency and time-domain features of the audio signal, and we utilize a long short-term memory network (LSTM) to capture the temporal features within the audio signal. We introduce a multi-scale graph attention network (MSGAT), which leverages the various implicit relationships between notes to enhance the interaction between different notes. Experimental results demonstrate that our model achieves high accuracy in detecting the onset and offset of notes on public datasets. In both frame-level and note-level metrics, DAFE-MSGAT achieves performance comparable to the state-of-the-art methods, showcasing exceptional transcription capabilities.

SFINet: A semantic feature interactive learning network for full-time infrared and visible image fusion

Infrared and visible image fusion aims to combine data from various source images to generate a high-quality image. Nevertheless, numerous fusion methods often prioritize visual quality above semantic information. To address this problem, we present a Semantic Feature Interactive Learning Network (SFINet) for full-time infrared and visible images. The SFINet encompasses an image fusion network and an image segmentation network through a Semantic Feature Interaction (SFI) module. The image fusion network employs Multi-scale Feature Extraction (MFE) modules to capture global and local information at multiple scales. Meanwhile, it performs an adaptive fusion of complementary information using a Dual Attention Feature Fusion (DAFF) module. The image segmentation network guides the image fusion network using the SFI module for semantic feature interaction. Comparative results prove that the proposed method is superior to state-of-the-art (SOTA) models in image fusion and semantic segmentation tasks. The code is available at https://github.com/songwenhao123/SFINet.

MSDAFL: molecular substructure-based dual attention feature learning framework for predicting drug-drug interactions.

Drug-drug interactions (DDIs) can cause unexpected adverse drug reactions, affecting treatment efficacy and patient safety. The need for computational methods to predict DDIs has been growing due to the necessity of identifying potential risks associated with drug combinations in advance. Although several deep learning methods have been recently proposed to predict DDIs, many overlook feature learning based on interactions between the substructures of drug pairs. In this work, we introduce a molecular Substructure-based Dual Attention Feature Learning framework (MSDAFL), designed to fully utilize the information between substructures of drug pairs to enhance the performance of DDI prediction. We employ a self-attention module to obtain a set number of self-attention vectors, which are associated with various substructural patterns of the drug molecule itself, while also extracting interaction vectors representing inter-substructure interactions between drugs through an interactive attention module. Subsequently, an interaction module based on cosine similarity is used to further capture the interactive characteristics between the self-attention vectors of drug pairs. We also perform normalization after the interaction feature extraction to mitigate overfitting. After applying three-fold cross-validation, the MSDAFL model achieved average precision scores of 0.9707, 0.9991, and 0.9987, and area under the receiver operating characteristic curve scores of 0.9874, 0.9934, and 0.9974 on three datasets, respectively. In addition, the experiment results of five-fold cross-validation and cross-datum study also indicate that MSDAFL performs well in predicting DDIs. Data and source codes are available at https://github.com/27167199/MSDAFL.

TAENet: Two-branch Autoencoder Network for Interpretable Deepfake Detection

Deepfake detection attracts increasingly attention due to serious security issues caused by facial manipulation techniques. Recently, deep learning-based detectors have achieved promising performance. However, these detectors suffer severe untrustworthy due to the lack of interpretability. Thus, it is essential to work on the interpretibility of deepfake detectors to improve the reliability and traceability of digital evidence. In this work, we propose a two-branch autoencoder network named TAENet for interpretable deepfake detection. TAENet is composed of Content Feature Disentanglement (CFD), Content Map Generation (CMG), and Classification. CFD extracts latent features of real and forged content with dual encoder and feature discriminator. CMG employs a Pixel-level Content Map Generation Loss (PCMGL) to guide the dual decoder in visualizing the latent representations of real and forged contents as real-map and fake-map. In classification module, the Auxiliary Classifier (AC) serves as map amplifier to improve the accuracy of real-map image extraction. Finally, the learned model decouples the input image into two maps that have the same size as the input, providing visualized evidence for deepfake detection. Extensive experiments demonstrate that TAENet can offer interpretability in deepfake detection without compromising accuracy.

A Fault Diagnosis Method for Electric Vehicle Lithium Power Batteries Based on Dual Feature Extraction from the Time and Frequency Domains

Abstract This study focuses on the safety and reliability issues of lithium-ion batteries, proposing a fault diagnosis strategy that leverages dual feature extraction in the time-frequency domains. Additionally, by modifying the traditional autoencoder, the study proposes a feature-guided autoencoder as an unsupervised model for extracting features in the time domain. Initially, wavelet packet decomposition and its energy denoising treatment are employed to refine fault information within battery voltage signals. Subsequently, the reconstruction error outputted by the Feature-Guided Autoencoder is utilized as the time-domain fault feature, while the cosine similarity of the energy of signals in various frequency bands obtained after wavelet packet decomposition serves as the frequency-domain fault feature. Ultimately, this paper selects the Isolation Forest algorithm for two-dimensional outlier detection of time-frequency features. Experimental results demonstrate that the Feature-Guided Autoencoder proposed in this study not only enhances the sensitivity of time-domain fault features compared to traditional autoencoders and their variants but also optimizes issues related to training time and computational load. The effectiveness of the proposed dual feature fault diagnosis method in both the time and frequency domains is validated through data from two actual vehicles, showing superior early fault detection capability relative to single-feature fault diagnosis methods.

A Multi-Branch Feature Extraction Residual Network for Lightweight Image Super-Resolution

Single-image super-resolution (SISR) seeks to elucidate the mapping relationships between low-resolution and high-resolution images. However, high-performance network models often entail a significant number of parameters and computations, presenting limitations in practical applications. Therefore, prioritizing a light weight and efficiency becomes crucial when applying image super-resolution (SR) to real-world scenarios. We propose a straightforward and efficient method, the Multi-Branch Feature Extraction Residual Network (MFERN), to tackle lightweight image SR through the fusion of multi-information self-calibration and multi-attention information. Specifically, we have devised a Multi-Branch Residual Feature Fusion Module (MRFFM) that leverages a multi-branch residual structure to succinctly and effectively fuse multiple pieces of information. Within the MRFFM, we have designed the Multi-Scale Attention Feature Fusion Block (MAFFB) to adeptly extract features via convolution and self-calibration attention operations. Furthermore, we introduce a Dual Feature Calibration Block (DFCB) to dynamically fuse feature information using dynamic weight values derived from the upper and lower branches. Additionally, to overcome the limitation of convolution in solely extracting local information, we incorporate a Transformer module to effectively integrate global information. The experimental results demonstrate that our MFERN exhibits outstanding performance in terms of model parameters and overall performance.

3DRecNet: A 3D Reconstruction Network with Dual Attention and Human-Inspired Memory

Humans inherently perceive 3D scenes using prior knowledge and visual perception, but 3D reconstruction in computer graphics is challenging due to complex object geometries, noisy backgrounds, and occlusions, leading to high time and space complexity. To addresses these challenges, this study introduces 3DRecNet, a compact 3D reconstruction architecture optimized for both efficiency and accuracy through five key modules. The first module, the Human-Inspired Memory Network (HIMNet), is designed for initial point cloud estimation, assisting in identifying and localizing objects in occluded and complex regions while preserving critical spatial information. Next, separate image and 3D encoders perform feature extraction from input images and initial point clouds. These features are combined using a dual attention-based feature fusion module, which emphasizes features from the image branch over those from the 3D encoding branch. This approach ensures independence from proposals at inference time and filters out irrelevant information, leading to more accurate and detailed reconstructions. Finally, a Decoder Branch transforms the fused features into a 3D representation. The integration of attention-based fusion with the memory network in 3DRecNet significantly enhances the overall reconstruction process. Experimental results on the benchmark datasets, such as ShapeNet, ObjectNet3D, and Pix3D, demonstrate that 3DRecNet outperforms existing methods.

INTEGRATING DUAL FUNDUS IMAGE DEEP FEATURE POOLING BASED ON CUP AND DISC SEGMENTATION FOR EFFICIENT GLAUCOMA DETECTION FRAMEWORK INDULGING HEURISTIC CONCEPT

The permanent damage occurring to the optical nerve, which transmits the visualized images to the brain leading to permanent vision loss, is called glaucoma. The detection and diagnosis of glaucoma at the beginning stage are essential to prevent permanent damage caused to vision as there are no initial symptoms to detect the onset of the damage, and there is no cure while the damage progresses to its extreme stage. Many models utilizing deep learning technology have been executed to identify the presence of glaucoma using digital Fundus Images (FI). However, these methods need specialized hardware and are computationally complicated as there is not much-labeled data available, leading to generalization issues in these models. Therefore, the development of a deep learning-oriented model for Glaucoma Detection (GD) using the dual feature pooling of cup and disc segmentation features with the aid of the FI is the main motive behind this work. At first, the digital FI is congregated from standardized online data sources. Then the gathered images are considered for the image segmentation procedure. The disc is segmented from the input image with the aid of the Transformer based Adaptive ResUNet++ (TA-ResUNet++) framework. The segmented disc image is now provided to hybrid convolution networks (HCN) for extracting the disc-oriented features. At the same time, the cup is segmented from the gathered input image using the executed TA-ResUnet++. Following this, the cup features are extracted using the same HCN model. The obtained features regarding the disc and the cup are concatenated in order to generate a single pool of glaucoma features. Then these features are inputted into the implemented bidirectional long short-term memory with multi-head attention (Bi-LSTM-MHA) mechanism to detect the presence of glaucoma in people. The segmentation and detection outcomes are made better by optimizing the parameters in the TA-ResUNet++ and Bi-LSTM-MHA models with the aid of hybrid sewing training with the Chameleon swarm optimization algorithm (HST-CSA). The experimental analysis is done to analyze the effective performance of the developed GD model. Jaccard analysis performed for the developed HST-CSOA-TA-ResUNet++-based disc segmentation gained better performance as 18.29% than MobileNet, 14.11% efficient than ResNet, 12.79% superior to Bi-LSTM and 5.43% higher than Bi-LSTM-MHA while considering best as the statistical measure.

Multi-objective evolutionary algorithm based on transfer learning and neural networks: Dual operator feature fusion and weight vector adaptation

In multi-objective evolutionary algorithms, one of the focal points is finding a balance between diversity and convergence. In decomposition-based algorithms, the role of weight vectors is crucial. Despite numerous studies dedicated to these aspects, there is a scarcity of utilizing transfer learning algorithms for dual-operator feature fusion and employing neural networks for accurate partitioning of the objective space population. To address the aforementioned issues, this paper proposes the following improvements: (1) Implementing a Balanced Distribution Adaptation (BDA) transfer learning algorithm to achieve dual-operator feature fusion, resulting in a transfer population guiding the adaptive adjustment of weight vectors. (2) Integrating the BDA algorithm with multi-objective algorithms requires labeling the data, a challenge in the multi-objective evolutionary algorithm. To tackle this issue, non-dominated sorting is introduced as a bridge connecting the BDA and multi-objective evolutionary algorithms. This serves as a method to combine the advantages of decomposition-based and Pareto-dominance principle-based multi-objective algorithms. (3) To overcome the impact of traditional Euclidean distance on population sparsity, a neural network is employed to determine the population's distribution in the objective space accurately. This ensures the precise identification of individuals to be removed from the current population and the areas where additions are needed. In order to fully validate the effectiveness of the proposed algorithm, four different sets of experiments are conducted in the experimental section, where three sets of benchmarking problems are compared to a variety of algorithms that have received much attention in recent years, as well as ablation experiments.

Boundary points guided 3D object detection for point clouds

3D object detection in LiDAR point clouds is crucial for computer vision tasks such as autonomous driving. The two-stage approach with point cloud completion achieves remarkable performance by generating semantic surface points for foreground objects or learning bird’s eye view shape heat map labels. However, these methods require additional completion datasets, leading to substantial computation and memory demands. In this context, we propose a Boundary Points Guided 3D (BPG3D) object detection method that complements point cloud boundary information without the need for additional data. Specifically, we generate Region of Interest (RoI) boundary points to aggregate the neighbor voxel information at the RoI boundary during the refinement stage to complement the missing boundary information. Meanwhile, we design a Dual Feature Selection (DFS) module to adaptively fuse RoI grid point features and RoI boundary point features for bounding box refinement with negligible computational cost. Additionally, inspired by tensor decomposition theory, we use low-rank tensors to reconstruct high-rank tensors in the point cloud feature encoder to enhance contextual semantic information. The proposed method achieves 65.81% mAP on KITTI Test Set, obtaining a good trade-off between accuracy and efficiency.

Low-light enhancement method with dual branch feature fusion and learnable regularized attention

Restricted by the lighting conditions, the images captured at night tend to suffer from color aberration, noise, and other unfavorable factors, making it difficult for subsequent vision-based applications. To solve this problem, we propose a two-stage size-controllable low-light enhancement method, named Dual Fusion Enhancement Net (DFEN). The whole algorithm is built on a double U-Net structure, implementing brightness adjustment and detail revision respectively. A dual branch feature fusion module is adopted to enhance its ability of feature extraction and aggregation. We also design a learnable regularized attention module to balance the enhancement effect on different regions. Besides, we introduce a cosine training strategy to smooth the transition of the training target from the brightness adjustment stage to the detail revision stage during the training process. The proposed DFEN is tested on several low-light datasets, and the experimental results demonstrate that the algorithm achieves superior enhancement results with the similar parameters. It is worth noting that the lightest DFEN model reaches 11 FPS for image size of 1224×1024 in an RTX 3090 GPU.Graphical

Best of two worlds: Efficient, usable and auditable biometric ABC on the blockchain

In García-Rodríguez et al. 2024, two generic constructions for biometric-based non-transferable Attribute Based Credentials (biometric ABC) are presented, which offer different trade-offs between efficiency and trust assumptions. In this paper, we focus on the second scheme denoted as BioABC-ZK that tries to remove the strong (and unrealistic) trust assumption on the Reader R, and we show that BioABC-ZK has a security flaw for a colluding R and Verifier V. Besides, BioABC-ZK lacks GDPR-compliance, which requires secure processing of biometrics, for instance in form of Fuzzy Extractors, as opposed to (i) storing the reference biometric template aBio in the user’s mobile phone and (ii) processing of biometrics using an external untrusted R, whose foreign manufacturers are unlikely to adjust their products according to GDPR.The contributions of this paper are threefold. First, we review efficient biometric ABC schemes to identify the privacy-by-design criteria for them. In view of these principles, we propose a new architecture for biometric ABC of Sarier 2021 by adapting the recently introduced core/helper setting. Briefly, a user in our modified setting is composed of a constrained core device (a SIM card) inside a helper device (a smart phone with dual SIM and face recognition feature), which – as opposed to García-Rodríguez et al. 2024 – does not need to store aBio. This way, the new design provides Identity Privacy without the need for an external R and/or a dedicated hardware per user such as a biometric smart card reader or a tamper proof smart card as in current hardware-bound credential systems. Besides, the new system maintains minimal hardware requirements on the SIM card – only responsible for storing ABC and helper data –, which results in easy adoption and usability without loosing efficiency, if deep face fuzzy vault and our modified ABC scheme are employed together. As a result, a total overhead of 500 ms to a showing of a comparable non-biometric ABC is obtained instead of the 2.1 s in García-Rodríguez et al. 2024 apart from the removal of computationally expensive pairings. Finally, as different from García-Rodríguez et al. 2024, auditing is achieved via Blockchain instead of proving in zero-knowledge the actual biometric matching by the user to reveal malicious behavior of R and V.

Application of the bicharacteristic attention residual pyramid for the treatment of brain tumors

Currently, surgery remains the primary treatment for craniocerebral tumors. Before doctors perform surgeries, they need to determine the surgical plan according to the shape, location, and size of the tumor; however, various conditions of different patients make the tumor segmentation task challenging. To improve the accuracy of determining tumor shape and realizing edge segmentation, a U-shaped network combining a residual pyramid module and a dual feature attention module is proposed. The residual pyramid module can enlarge the receptive field, extract multiscale features, and fuse original information, which solves the problem caused by the feature pyramid pooling where the local information is not related to the remote information. In addition, the dual feature attention module is proposed to replace the skip connection in the original U-Net network, enrich the features, and improve the attention of the model to space and channel features with large amounts of information to be used for more accurate brain tumor segmentation. To evaluate the performance of the proposed model, experiments were conducted on the public datasets Kaggle_3M and BraTS2021. Because the model proposed in this study is applicable to two-dimensional image segmentation, it is necessary to obtain the crosscutting images of fair class in the BraTS2021 dataset in advance. Results show that the model accuracy, Jaccard similarity coefficient, Dice similarity coefficient, and false negative rate (FNR) on the Kaggle_3M dataset are 0.9395, 0.8812, 0.8958, and 0.007, respectively. The model accuracy, Jaccard similarity coefficient, Dice similarity coefficient, and FNR on the BraTS2021 dataset were 0.9375, 0.9072, 0.8981, and 0.0087, respectively. Compared with existing algorithms, all the indicators of the proposed algorithm have been improved, but the proposed model still has certain limitations and has not been applied to actual clinical trials. For specific datasets, the generalization ability of the model needs to be further improved. In the future work, the model will be further improved to address the aforementioned limitations.