Feature Refinement Research Articles

Hiding image into image with hybrid attention mechanism based on GANs

AbstractImage steganography is the art of concealing secret information within images to prevent detection. In deep‐learning‐based image steganography, a common practice is to fuse the secret image with the cover image to directly generate the stego image. However, not all features are equally critical for data hiding, and some insignificant ones may lead to the appearance of residual artifacts in the stego image. In this article, a novel network architecture for image steganography with hybrid attention mechanism based on generative adversarial network is introduced. This model consists of three subnetworks: a generator for generate stego images, an extractor for extracting the secret images, and a discriminator to simulate the detection process, which aids the generator in producing more realistic stego images. A specific hybrid attention mechanism (HAM) module is designed that effectively fuses information across channel and spatial domains, facilitating adaptive feature refinement within deep image representations. The experimental results suggest that the HAM module not only enhances the image quality during both the steganography and extraction processes but also improves the model's undetectability. Stego images are mixed with varying levels of noise in the training process, which can further improve robustness. Finally, it is verified that the model outperforms current steganography approaches on three datasets and exhibits good undetectability.

Arbitrary stylized light-field generation for three-dimensional light-field displays based on radiance fields.

Three-dimensional (3D) light-field display technology can reconstruct the spatial characteristics of 3D scenes and provide users with an immersive visual experience without the need for any additional external devices. Here, an arbitrary stylized light-field generation method for 3D light-field displays is presented, and the tripartite constraints are addressed by conducting style transformation in a refined feature space. A multi-dimensional feature refinement module is designed to learn which aspects and regions should be prioritized within the high-level feature grid of the scene, which allows content and style patterns to be better matched and blended. To preserve more structural details and reduce artifacts, a novel global quality and local structure joint loss function is used for optimization. A mask-guided light-field coding method based on ray-casting is employed to accelerate the synthesis of stylized light-field images. Experimental results demonstrate that the proposed method can generate higher-quality stylized 3D light-field content with any given style in a zero-shot manner. Additionally, the method provides two user control extensions to further enrich the ways for the personalized editing of 3D content displayed on 3D light-field displays.

GRLN: Gait Refined Lateral Network for gait recognition

Gait recognition aims to identify individuals at a distance based on their biometric gait patterns. While offering flexibility in network input, existing set-based methods often overlook the potential of fine-grained local feature by solely utilizing global gait feature and fail to fully exploit the communication between silhouette-level and set-level features. To alleviate this issue, we propose Gait Refined Lateral Network(GRLN), featuring plug-and-play Adaptive Feature Refinement modules (AFR) that extract discriminative features progressively from silhouette-level and set-level representations in a coarse-to-fine manner at various network depths. AFR can be widely applied in set-based gait recognition models to substantially enhance their gait recognition performance. To align with the extracted refined features, we introduce Horizontal Stable Mapping (HSM), a novel mapping technique that reduces model parameters while improving experimental results. To demonstrate the effectiveness of our method, we evaluate GRLN on two gait datasets, achieving the highest recognition rate among all set-based methods. Specifically, GRLN demonstrates an average improvement of 1.15% over the state-of-the-art set-based method on CASIA-B. Especially in the coat-wearing condition, GRLN exhibits a 5% improvement in performance compared to the contrast method GLN.

Context-aware semantic segmentation network for tunnel face feature identification

The automated interpretation of tunnel face geological information is significant to the construction decision-making of rock mass engineering. An intelligent recognition algorithm, named the Transformer and Convolution neural networks Semantic segmentation Network (TCSeNet), is introduced to overcome the low interpretation accuracy caused by certain limitations of existing automated interpretation methods. Firstly, a hybrid encoder is constructed to extract global and local context information using Transformer and Convolution Neural Networks, respectively. Furthermore, a context feature adaptive selection module is designed to cross-fusion the information. Secondly, a feature pyramid-like decoder is constructed for multi-scale object problems. Furthermore, a multi-scale feature refinement module is designed to improve the ability of multi-scale feature expression. A tunnel face dataset is constructed for training and testing. The research shows that the mIoU of TCSeNet reaches 92.57%. This indicates that the TCSeNet is suitable for automatic interpretation of tunnel face geological information.

A Fault Diagnosis Method for Analog Circuits Based on Improved TQWT and Inception Model

A soft fault in an analog circuit is a symptom where the parameter range of a component exists symmetrically to the left and right of its nominal value and exceeds a specific range. The proposed method uses the Grey Wolf Optimization (GWO) optimized tunable Q-factor wavelet transform (TQWT) algorithm for feature refinement, the Inception model for feature extraction, and an SVM for fault diagnosis. First, the Q-factor is optimized to make it more compatible with the signal. Second, the signal is decomposed, and a single-branch reconstruction is performed using the TQWT to extract features adequately. Then, fault feature extraction is conducted using the Inception model to obtain multiscale features. Finally, a Support Vector Machine (SVM) is used to complete the entire fault diagnosis process. The proposed method is comprehensively evaluated using the Sallen–Key bandpass filter circuit and the four-op-amp biquad high-pass filter circuit widely used in electronic systems. The experimental results prove that the proposed method outperforms the existing methods in terms of diagnosis accuracy and reliability.

MMFG: Multimodal-based Mutual Feature Gating 3D Object Detection

To address the problem that image and point cloud features are fused in a coarse fusion way and cannot achieve deep fusion, this paper proposes a multimodal 3D object detection architecture based on a mutual feature gating mechanism. First, since the feature aggregation approach based on the set abstraction layer cannot obtain fine-grained features, a point-based self-attention mechanism module is designed. This module is added to the extraction branch of point cloud features to achieve fine-grained feature aggregation while maintaining accurate location information. Second, a new gating mechanism is designed for the deep fusion of image and point cloud. Deep fusion is achieved by mutual feature weighting between the image and the point cloud. The newly fused features are then fed into a feature refinement network to extract classification confidence and 3D target bounding boxes. Finally, a multi-scale detection architecture is proposed to obtain a more complete object shape. The location-based encoding feature algorithm is also designed to focus the interest points in the region of interest adaptively. The whole architecture shows outstanding performance on the KITTI3D and nuSenece datasets, especially at the difficult level. It shows that the framework solves the problem of low detection rates in LiDAR mode due to the low number of surface points obtained from distant objects.

DSTAN: A Deformable Spatial-temporal Attention Network with Bidirectional Sequence Feature Refinement for Speckle Noise Removal in Thyroid Ultrasound Video.

Thyroid ultrasound video provides significant value for thyroid diseases diagnosis, but the ultrasound imaging process is often affected by the speckle noise, resulting in poor quality of the ultrasound video. Numerous video denoising methods have been proposed to remove noise while preserving texture details. However, existing methods still suffer from the following problems: (1) relevant temporal features in the low-contrast ultrasound video cannot be accurately aligned and effectively aggregated by simple optical flow or motion estimation, resulting in the artifacts and motion blur in the video; (2) fixed receptive field in spatial features integration lacks the flexibility of aggregating features in the global region of interest and is susceptible to interference from irrelevant noisy regions. In this work, we propose a deformable spatial-temporal attention denoising network to remove speckle noise in thyroid ultrasound video. The entire network follows the bidirectional feature propagation mechanism to efficiently exploit the spatial-temporal information of the whole video sequence. In this process, two modules are proposed to address the above problems: (1) a deformable temporal attention module (DTAM) is designed after optical flow pre-alignment to further capture and aggregate relevant temporal features according to the learned offsets between frames, so that inter-frame information can be better exploited even with the imprecise flow estimation under the low contrast of ultrasound video; (2) a deformable spatial attention module (DSAM) is proposed to flexibly integrate spatial features in the global region of interest through the learned intra-frame offsets, so that irrelevant noisy information can be ignored and essential information can be precisely exploited. Finally, all these refined features are rectified and merged through residual convolution blocks to recover the clean video frames. Experimental results on our thyroid ultrasound video (US-V) dataset and the DDTI dataset demonstrate that our proposed method exceeds 1.2 1.3dB on PSNR and has clearer texture detail compared to other state-of-the-art methods. In the meantime, the proposed model can also assist thyroid nodule segmentation methods to achieve more accurate segmentation effect, which provides an important basis for thyroid diagnosis. In the future, the proposed model can be improved and extended to other medical image sequence datasets, including CT and MRI slice denoising. The code and datasets are provided at https://github.com/Meta-MJ/DSTAN .

MFUR-Net: Multimodal feature fusion and unimodal feature refinement for RGB-D salient object detection

RGB-D salient object detection aims to integrate multimodal feature information for accurate salient region localization. Despite the development of several RGB-D salient object detection models, existing methods face challenges in effectively fusing RGB with Depth features to exploit their complementary aspects. To address this challenge, this study introduces MFUR-Net, a network based on multimodal feature fusion and unimodal feature refinement. The contributions of this study are primarily threefold: First, a multimodal multilevel feature fusion module is proposed at the encoder stage to integrate multimodal and multilevel features, generating enhanced RGB-D features; Second, a multi-input feature aggregation module at the decoder stage is introduced, which incorporates the RGB and Depth feature streams into the RGB-D feature streams so that they collaborate with the RGB-D features to learn more discriminative information related to the salient object; Third, a unimodal saliency feature refinement module is introduced to refine saliency feature information across modalities and eliminate redundancy before the integration of feature streams into the decoder; With the gradual refinement of saliency features, MFUR-Net achieves accurate saliency map prediction at the decoder stage. This method has been validated through extensive experiments on seven recognized datasets, demonstrating significant advantages over existing state-of-the-art techniques in key performance metrics. The source code can be found in https://github.com/wangwei678/MFUR-Net.

Optimizing cardiovascular image segmentation through integrated hierarchical features and attention mechanisms.

Cardiovascular diseases are the top cause of death in China. Manual segmentation of cardiovascular images, prone to errors, demands an automated, rapid, and precise solution for clinical diagnosis. The paper highlights deep learning in automatic cardiovascular image segmentation, efficiently identifying pixel regions of interest for auxiliary diagnosis and research in cardiovascular diseases. In our study, we introduce innovative Region Weighted Fusion (RWF) and Shape Feature Refinement (SFR) modules, utilizing polarized self-attention for significant performance improvement in multiscale feature integration and shape fine-tuning. The RWF module includes reshaping, weight computation, and feature fusion, enhancing high-resolution attention computation and reducing information loss. Model optimization through loss functions offers a more reliable solution for cardiovascular medical image processing. Our method excels in segmentation accuracy, emphasizing the vital role of the RWF module. It demonstrates outstanding performance in cardiovascular image segmentation, potentially raising clinical practice standards. Our method ensures reliable medical image processing, guiding cardiovascular segmentation for future advancements in practical healthcare and contributing scientifically to enhanced disease diagnosis and treatment.

Survey of machine learning techniques for Arabic fake news detection

Social media platforms have emerged as primary information sources, offering easy access to a wide audience. Consequently, a significant portion of the global population relies on these platforms for updates on current events. However, fraudulent actors exploit social networks to disseminate false information, either for financial gain or to manipulate public opinion. Recognizing the detrimental impact of fake news, researchers have turned their attention to automating its detection. In this paper, we provide a thorough review of fake news detection in Arabic, a low-resource language, to contextualize the current state of research in this domain. In our research methodology, we recall fake news terminology, provide examples for clarity, particularly in Arabic contexts, and explore its impact on public opinion. We discuss the challenges in fake news detection, outline the used datasets, and provide Arabic annotation samples for label assignment. Likewise, preprocessing steps for Arabic language nuances are highlighted. We also explore features from shared tasks and their implications. Lastly, we address open issues, proposing some future research directions like dataset improvement, feature refinement, and increased awareness to combat fake news proliferation. We contend that incorporating our perspective into the examination of fake news aspects, along with suggesting enhancements, sets this survey apart from others currently available.

Securing Edge Devices: Malware Classification with Dual-Attention Deep Network

Detecting malware is a crucial defense mechanism against potential cyber-attacks. However, current methods illustrate significant limitations in achieving high performance while maintaining faster inference on edge devices. This study proposes a novel deep network with dual-attention feature refinement on a two-branch deep network to learn real-time malware detection on edge platforms. The proposed method introduces lightweight spatial-asymmetric attention for refining the extracted features of its backbone and multi-head attention to correlate learned features from the network branches. The experimental results show that the proposed method can significantly outperform existing methods in quantitative evaluation. In addition, this study also illustrates the practicability of a lightweight deep network on edge devices by optimizing and deploying the model directly on the actual edge hardware. The proposed optimization strategy achieves a frame rate of over 545 per second on low-power edge devices.

MANet: Mixed Attention Network for Visual Explanation

Various visual explanation methods, such as CAM and Grad-CAM, have been proposed to visualize and interpret predictions made by CNNs. Recent efforts go beyond mere visual interpretability, aiming to enhance CNN performance through the utilization of these generated visual explanations. In this work, we propose MANet (Mixed Attention Network)—a network architecture that advances the stability of visual explanations through an adaptive feature refinement mechanism via a mixed attention module. Concurrently, the generated attention maps are harnessed to bolster network performance in image recognition tasks. Experimental findings underscore the efficacy of MANet, demonstrating improved visual stability and consistency. The proposed architecture not only surpasses baseline models in image classification and object detection tasks but also establishes a novel paradigm for synergizing visual interpretability and network performance enhancement.

DLA-Net: dual lesion attention network for classification of pneumoconiosis using chest X-ray images

Accurate and early detection of pneumoconiosis using chest X-rays (CXR) is important for preventing the progression of this incurable disease. It is also a challenging task due to large variations in appearance, size and location of lesions in the lung regions as well as inter-class similarity and intra-class variance. Compared to traditional methods, Convolutional Neural Networks-based methods have shown improved results; however, these methods are still not applicable in clinical practice due to limited performance. In some cases, limited computing resources make it impractical to develop a model using whole CXR images. To address this problem, the lung fields are divided into six zones, each zone is classified separately and the zone classification results are then aggregated into an image classification score, based on state-of-the-art. In this study, we propose a dual lesion attention network (DLA-Net) for the classification of pneumoconiosis that can extract features from affected regions in a lung. This network consists of two main components: feature extraction and feature refinement. Feature extraction uses the pre-trained Xception model as the backbone to extract semantic information. To emphasise the lesion regions and improve the feature representation capability, the feature refinement component uses a DLA module that consists of two sub modules: channel attention (CA) and spatial attention (SA). The CA module focuses on the most important channels in the feature maps extracted by the backbone model, and the SA module highlights the spatial details of the affected regions. Thus, both attention modules combine to extract discriminative and rich contextual features to improve classification performance on pneumoconiosis. Experimental results show that the proposed DLA-Net outperforms state-of-the-art methods for pneumoconiosis classification.

Res2Net-based multi-scale and multi-attention model for traffic scene image classification.

With the increasing applications of traffic scene image classification in intelligent transportation systems, there is a growing demand for improved accuracy and robustness in this classification task. However, due to weather conditions, time, lighting variations, and annotation costs, traditional deep learning methods still have limitations in extracting complex traffic scene features and achieving higher recognition accuracy. The previous classification methods for traffic scene images had gaps in multi-scale feature extraction and the combination of frequency domain, spatial, and channel attention. To address these issues, this paper proposes a multi-scale and multi-attention model based on Res2Net. Our proposed framework introduces an Adaptive Feature Refinement Pyramid Module (AFRPM) to enhance multi-scale feature extraction, thus improving the accuracy of traffic scene image classification. Additionally, we integrate frequency domain and spatial-channel attention mechanisms to develop recognition capabilities for complex backgrounds, objects of different scales, and local details in traffic scene images. The paper conducts the task of classifying traffic scene images using the Traffic-Net dataset. The experimental results demonstrate that our model achieves an accuracy of 96.88% on this dataset, which is an improvement of approximately 2% compared to the baseline Res2Net network. Furthermore, we validate the effectiveness of the proposed modules through ablation experiments.

Abusive Comment Detection in Tamil Code-Mixed Data by Adjusting Class Weights and Refining Features

In recent years, a significant portion of the content on various platforms on the internet has been found to be offensive or abusive. Abusive comment detection can go a long way in preventing internet users from facing the adverse effects of coming in contact with abusive language. This problem is particularly challenging when the comments are found in low-resource languages like Tamil or Tamil-English code-mixed text. So far, there has not been any substantial work on abusive comment detection using imbalanced datasets. Furthermore, significant work has not been performed, especially for Tamil code-mixed data, that involves analysing the dataset for classification and accordingly creating a custom vocabulary for preprocessing. This paper proposes a novel approach to classify abusive comments from an imbalanced dataset using a customised training vocabulary and a combination of statistical feature selection with language-agnostic feature selection while making use of explainable AI for feature refinement. Our model achieved an accuracy of 74% and a macro F1-score of 0.46.

Synergistic fusion network for landslide segmentation: the vital complementarity of geological information to remote sensing imagery

In the contemporary technological environment, access to a multitude of data sources, such as digital elevation models (DEM), slope data, and other geological information, has become essential for augmenting remote sensing imagery in landslide analysis. These datasets enhance landslide identification capabilities, but existing methods often fail to fully leverage their unique characteristics due to oversimplified fusion strategies. To overcome this challenge, we introduce the Synergistic Fusion Network (SFNet), which is specifically designed to utilize the complementary nature of geological data to significantly improve the accuracy and efficiency of landslide segmentation. SFNet incorporates Multi-Source Fusion Modules (MSFM) and Reverse Feature Refinement Modules(RFRM), through an innovative network architecture, enhancing remote sensing imagery with integrated geological information. In our experiments, SFNet outperforms existing mainstream networks, demonstrating superior F1 scores, thereby showcasing its ability to effectively segment landslide regions with high precision. This advancement highlights the importance of considering the unique contributions of each data source, especially the complementary effects of geological information.

Heterogeneous Fusion and Integrity Learning Network for RGB-D Salient Object Detection

While significant progress has been made in recent years in the field of salient object detection, there are still limitations in heterogeneous modality fusion and salient feature integrity learning. The former is primarily attributed to a paucity of attention from researchers to the fusion of cross-scale information between different modalities during processing multi-modal heterogeneous data, coupled with an absence of methods for adaptive control of their respective contributions. The latter constraint stems from the shortcomings in existing approaches concerning the prediction of salient region’s integrity. To address these problems, we propose a Heterogeneous Fusion and Integrity Learning Network for RGB-D Salient Object Detection (HFIL-Net). In response to the first challenge, we design an Advanced Semantic Guidance Aggregation (ASGA) module, which utilizes three fusion blocks to achieve the aggregation of three types of information: within-scale cross-modal, within-modal cross-scale, and cross-modal cross-scale. In addition, we embed the local fusion factor matrices in the ASGA module and utilize the global fusion factor matrices in the Multi-modal Information Adaptive Fusion module to control the contributions adaptively from different perspectives during the fusion process. For the second issue, we introduce the Feature Integrity Learning and Refinement Module. It leverages the idea of ”part-whole” relationships from capsule networks to learn feature integrity and further refine the learned features through attention mechanisms. Extensive experimental results demonstrate that our proposed HFIL-Net outperforms over 17 state-of-the-art detection methods in testing across seven challenging standard datasets. Codes and results are available on https://github.com/BojueGao/HFIL-Net .

Multi-Bottleneck progressive propulsion network for medical image semantic segmentation with integrated macro-micro dual-stage feature enhancement and refinement

Semantic segmentation can assist doctors to locate key lesion areas intelligently, rapidly and with high precision in medical imaging, which is of great clinical significance for the diagnosis and rehabilitation of patients in various medical fields such as oncology and neurology. Existing segmentation networks face accuracy bottlenecks because enriched information at the decoding end can’t disperse over multiple layers of semantic depth. This is compounded by challenges like complex anatomical structures and varying imaging modalities. In this study, we propose a Multi-Bottleneck Progressive Semantic Segmentation Network (MBP-SSNet), which is essentially a new Baseline based on our proposal: Multi-Bottleneck based Progressive Propulsion Feature Guidance Network (MB-PPFG Net). Its Multi-Bottleneck solves the problem of coding and decoding multiplexed transmission of enriched information, and the propulsive transmission alleviates the problem of insufficient semantic fusion. In addition, under the macro–micro processing idea, MacroFocus Pre-Bottleneck Feature Enhancer (MPBFE) is proposed at the codec intersection in order to better enhance the image contextual semantic dependency association; while MicroDetail Post- Decoding Feature Refiner (MPDFR) is proposed at the tail of the network for fine-grained polishing. In the experiment, the MBP-SSNet was compared with 17 other models across 7 datasets, including diverse medical imaging scenarios, involving metric exploration, image comparison, process validation, and statistical analysis. Concurrently, 22 types of ablation analyses were conducted on it, along with detailed discussions on two critical issues. The experimental results demonstrate that MBP-SSNet achieves an average performance improvement of 0.6809 % in medical image segmentation compared to the optimal benchmark model. The official web address of MBP-SSNet is at: https://github.com/YF-W/MBP-SSNet.

Masked face recognition using domain adaptation

Wearing facial masks has become a must in our daily life due to the global COVID-19 pandemic. However, the performance of a face recognition system is severely degraded due to the fact that the face images in the gallery are unmasked faces while the probe face images captured by the camera are masked faces, making the probe face images different from gallery face images in the activated region and the distribution domain. In this paper, we propose a novel face recognition system to address the issue. The system is integrated with a domain adaptation layer and a feature refinement layer. The feature refinement layer is based on the structure of the self-attention mechanism to align activated regions of unmasked faces with those of masked faces. The domain adaptation layer works by adapting the system from the unmasked face domain to the synthetically masked face domain and the real- world masked face domain. The system is tested on real-world data through face verification and face identification. The face verification accuracy is improved by 6.83% for the RMFD_FV dataset and 4.2% for the MFR2 dataset, and the face identification accuracy is improved by 15.43% for the MFRFI dataset.

Performance Scrutiny of Price Prediction on Blockchain Technology Using Machine Learning

Objective: This study, aiming to assess the accurateness of machine learning algorithms for the prediction of cryptocurrency prices, using blockchain technology, was conducted to attest to its effectiveness. The main goal is to evaluate the precision, solidity, and prospects of such models under variable and fragmented trading premises. Methodology: Dataset containing historical crypto prices, transaction volumes, emotions of investors, etc. is formed from different and various sources. Different machine learning approaches including linear regression, support vector machine, random forest, and deep learning networks will be used to construct the prediction model. The split of the dataset into training and testing subsets is performed to better evaluate and estimate the models' performance. Feature engineering techniques and parameter tuning are included in the process of making models more precise. Models are the ones which are the trained using historical data and then later tested out on the unseen data for the purpose of accurate results and generalization power. Results and Discussion: From the experiment it is evident that a shift of different machine learning algorithms exhibits differing outcomes. While certain models can yield admirable results in forecasting crypto prices in shorter terms, however, there are some models that are not capable of capturing the complicated impurities. Factors like data quality, function selection and model complexity are at the core of predictive power. The learning networks demonstrated the capability to reproduce nonlinearity and temporal relatedness in cryptocurrency value data. Conclusion: Cryptocurrency forecasting through blockchain technology involves the use of machine learning techniques which has a lot of potential. The success of these models also depends on the quality of the data, feature refinement and model choice. Research progress should focus on refining currently existing models, considering new data inputs, and introduction of advanced machine learning methods which should be able to increase forecast accuracy in rapidly changing cryptocurrency markets.