LMBF-Net: A Lightweight Multipath Bidirectional Focal Attention Network For Multifeatures Segmentation

BiGCAN: A novel SRS-based bidirectional graph Convolution Attention Network for dynamic user preference and next-item recommendation

Image-text matching by deep models has recently made remarkable achievements in many tasks, such as image caption and image search. A major challenge of matching the image and text lies in that they usually have complicated underlying relations between them and simply modeling the relations may lead to suboptimal performance. In this paper, we develop a novel approach Bi-directional Spatial-Semantic Attention Networks (BSSAN), which leverages both the word to regions (W2R) relation and image object to words (O2W) relation in a holistic deep framework for more effectively matching. Specifically, to effectively encode the W2R relation, we adopt LSTM with bilinear attention function to infer the image regions which are more related to the particular words, which is referred as the W2R attention network. On the other side, the O2W attention network is proposed to discover the semanticallyclose words for each visual object in the image, i.e., the visual object to words (O2W) relation. Then a deep model unifying both of the two directional attention networks into a holistic learning framework is proposed to learn the matching scores of image and text pairs. Compared to existing image-text matching methods, our approach achieves state-of-the-art performance on the datasets of Flickr30K and MSCOCO.

Visual-textual sentiment classification with bi-directional multi-level attention networks

In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural networks. The structure of this mechanism derives from a strong conceptual foundation of neural machine translation, and presents a light-weight mechanism for adaptive control of computation similar to the dynamic nature of recurrent neural networks. We introduce bidirectional attention modules that utilize the feed-forward feature maps and incorporate the global context to filter out ambiguity. Extensive experiments reveal the high degree of capability of this bidirectional attention model over feed-forward baselines and other state-of-the-art methods for monocular depth estimation on two challenging datasets - KITTI and DIODE. We show that our proposed approach either outperforms or performs at least on a par with the state-of-the-art monocular depth estimation methods with less memory and computational complexity.

High-resolution magnetic resonance (MR) imaging has attracted much attention due to its contribution to clinical diagnoses and treatment. However, because of the interference of noise and the limitation of imaging equipment, it is expensive to generate a satisfactory image. Super-resolution (SR) is a technique that enhances an imaging system’s resolution, which is effective and cost-efficient for MR imaging. In recent years, deep learning-based SR methods have made remarkable progress on natural images but not on medical images. Most existing medical images SR algorithms focus on the spatial information of a single image but ignore the temporal correlation between medical images sequence. We proposed two novel architectures for single medical image and sequential medical images, respectively. The multi-scale back-projection network (MSBPN) is constructed of several different scale back-projection units which consist of iterative up- and down-sampling layers. The multi-scale machine extracts different scale spatial information and strengthens the information fusion for a single image. Based on MSBPN, we proposed an accurate and lightweight Multi-Scale Bidirectional Fusion Attention Network(MSBFAN) that combines temporal information iteratively. That supplementary temporal information is extracted from the adjacent image sequence of the target image. The MSBFAN can effectively learn both the spatio-temporal dependencies and the iterative refinement process with only a lightweight number of parameters. Experimental results demonstrate that our MSBPN and MSBFAN are outperforming current SR methods in terms of reconstruction accuracy and parameter quantity of the model.

Ocean fronts are a mesoscale phenomenon in the ocean. It is important for fisheries, environmental protection, and military activities. Therefore, more and more attention has been attracted to ocean front detection. However, the distribution of front and non-front pixels is highly unbalanced in remote sensing images, and it is not easy to establish an effective ocean front detection algorithm with high accuracy. To alleviate these problems, we model the problem of detecting ocean fronts as an edge detection task and design a new end-to-end bi-directional progressive fusion attention network (BPFANet). Specifically, BPFANet consists of an effective backbone and a bi-directional path. The whole backbone has four stage detection blocks (SD blocks), which capture the ocean front features at different scales. Each SD block contains a side branch structure, which includes a deep residual dilated convolution (DRDC) module to enrich multi-scale edge information and an attention module (AM) to enhance the feature representation in both the channel and spatial dimensions. In addition, the bi-directional path can progressively fuse the four SD blocks of ocean front information. To evaluate BPFANet, we perform experiments on the OFDS365 dataset and show its advantages over existing ocean front detection methods.

Point cloud completion is a necessary task in real-world applications of recovering a complete geometry from missing regions of 3D objects. Furthermore, model efficiency is of vital importance in computer vision. In this paper, we present an efficient encoder–decoder network that predicts missing point clouds on the basis of incomplete point clouds. There are several advantages to this approach. First, a Mixed Attention Module (MAM) was implemented to obtain the correlational information of points. Second, the proposed Bidirectional Point Pyramid Attention Network (BiPPAN) can achieve simple and fast multiscale feature fusion to capture important features. Lastly, the designed encoder–decoder framework comprises skip connections to capture long-distance dependencies and structural information. We can conclude from the results of the experiments that the proposed network is an efficient and effective method to accomplish point cloud completion tasks.

Quality prediction, as the basis of quality control, is dedicated to predicting quality indices of the manufacturing process. In recent years, data-driven deep learning methods have received a lot of attention due to their accuracy, robustness, and convenience for the prediction of quality indices. However, the existing studies mainly focus on the quality prediction of a single machine, while ignoring dependency relationships among multiple machines in multistage manufacturing process. To tackle the above issues, a novel path enhanced bidirectional graph attention network (PGAT) is proposed in this article. PGAT models the dependencies among machines into directed graphs and introduces graph attention network to encode the dependencies. Nonetheless, it is difficult for graph neural networks to encode long-distance dependencies. Hence, dependency path information is introduced into the features of machines. Moreover, in order to solve the label noise problem that often occurs in actual industrial dataset, a masked loss function is devised. With its help, batch training with noisy labels can be achieved, which improves the training efficiency. Furthermore, experiments are conducted on a public quality prediction dataset collected from an actual production line. PGAT achieves the state-of-the-art results on this dataset, which confirms the effectiveness of PGAT. Additionally, the experimental results demonstrate the critical role of modeling dependency relationships among machines.

Introduction: Heart ailments are one of the foremost causes of global mortality; thus, an early and accurate diagnosis is paramount. ECG is a common method for evaluating heart conditions, often considered lacking prognostic accuracy. To support diagnostic accuracy, machine learning and AI are beginning to be used for automated ECG analysis. Objectives: The major objective is to develop and evaluate a new deep learning-based hybrid model that can leverage better classification accuracy and computational efficiency. Methods: In this research article, a deep learning approach is presented that integrates convolutional neural networks (CNNs) for feature extraction from the signal into a sequential fashion by using bidirectional long short-term memory (Bi-LSTM) and gated recurrent units (GRU) supplemented with attention mechanisms. A hybrid model is proposed and tested on the ECG Heartbeat Classification Dataset (MIT-BIH), which is known as the Bidirectional Recurrent Attention Network (BRAN). Results: With an astonishing accuracy of 99.65%, the proposed BRAN model surpasses existing methods in both classification accuracy and computational efficiency. This showcases the efficacy of merging CNN with recurrent architectures and attention mechanisms in ECG-based heart disease detection. Conclusions: The study confirms that deep learning models, especially the BRAN hybrid type, greatly enhance the recognition of heart disease from ECG data. The findings emphasize AI-assisted diagnosis inheriting higher accuracy and automation capability, which can help the medical personnel in turning towards early diagnosis and treatment. Real-time implementation and further validation over multiple datasets can be a consideration for future research.

The graph attention network (GAT) [1] has started to become a mainstream neural network architecture since 2018, yielding remarkable performance gains in various natural language processing (NLP) tasks. Although GAT has reached the state-of-the-art (SOTA) performance as a recent success in relation prediction in knowledge graph, the current model is still limited by the following two aspects: (1) the existing model only considers the neighbors from the inbound-direction of the given entity, but ignores the rich neighborhood information from outbound-directions; (2) the existing model only uses the $k$ -th hop output to learn the multi-hop embeddings, which leads to the loss of a large amount of early-stage embedding information (e.g., one-hop) at the graph attention step. In this study, we propose a novel bidirectional graph attention network (BiGAT) to learn the hierarchical neighbor propagation. In our proposed BiGAT, an inbound-directional GAT and an outbound-directional GAT are introduced to capture sufficient neighborhood information before propagating the bidirectional neighborhood information to learn the multi-hop feature embeddings in a hierarchical manner. Experiments conducted on the four publicly available datasets show that BiGAT achieves the competitive results in comparison to other SOTA methods.

Information dissemination on social media is often accompanied by a large number of false or true rumors. The spread of these rumors on social network platforms does serious harm to social stability. Traditional rumor detection methods use text or image contents to identify rumors, but the performance is not satisfactory. Deep detection models combined with deep learning algorithms are developed recently. In this study, a new bi-directional graph attention network (Bi-GAT) model is proposed for rumor detection, where two directions of rumor information propagation are considered at the same time. Firstly, rumor information is transformed into a bi-directional graph structure form, simultaneously. Secondly, the feature of each node is extracted and input to graph attention network with the graph structure information, where the multi-head attention mechanism is adopted. Thirdly, after being processed via two graph attention layers, the two-directional data are concatenated and input to a fully connected layer. The results of rumor classification can be obtained according to the output of the fully connected layer. The simulation results on some open datasets demonstrate the validity of the proposed model.

Many super-resolution (SR) algorithms have been proposed to increase image resolution. However, full-reference (FR) image quality assessment (IQA) metrics for comparing and evaluating different SR algorithms are limited. In this work, we propose the Perception-oriented Bidirectional Attention Network (PBAN) for image SR FR-IQA, which is composed of three modules: an image encoder module, a perception-oriented bidirectional attention (PBA) module, and a quality prediction module. First, we encode the input images for feature representations. Inspired by the characteristics of the human visual system, we then construct the perception-oriented PBA module. Specifically, different from existing attention-based SR IQA methods, we conceive a Bidirectional Attention to bidirectionally construct visual attention to distortion, which is consistent with the generation and evaluation processes of SR images. To further guide the quality assessment towards the perception of distorted information, we propose Grouped Multi-scale Deformable Convolution, enabling the proposed method to adaptively perceive distortion. Moreover, we design Sub-information Excitation Convolution to direct visual perception to both sub-pixel and sub-channel attention. Finally, the quality prediction module is exploited to integrate quality-aware features and regress quality scores. Extensive experiments demonstrate that our proposed PBAN outperforms state-of-the-art quality assessment methods.

Automatic surgical instrument segmentation is a crucial step for robotic-aided surgery. Encoder-decoder construction-based methods often directly fuse high-level and low-level features by skip connection to supplement some detailed information. However, irrelevant information fusion also increases misclassification or wrong segmentation, especially for complex surgical scenes. Uneven illumination always results in instruments similar to other tissues of background, which greatly increases the difficulty of automatic surgical instrument segmentation. The paper proposes a novel network to solve the problem. The paper proposes to guide the network to select effective features for instrument segmentation. The network is named context-guided bidirectional attention network (CGBANet). The guidance connection attention (GCA) module is inserted into the network to adaptively filter out irrelevant low-level features. Moreover, we propose bidirectional attention (BA) module for the GCA module to capture both local information and local-global dependency for surgical scenes to provide accurate instrument features. The superiority of our CGBA-Net is verified by multiple instrument segmentation on two publicly available datasets of different surgical scenarios, including an endoscopic vision dataset (EndoVis 2018) and a cataract surgery dataset. Extensive experimental results demonstrate our CGBA-Net outperforms the state-of-the-art methods on two datasets. Ablation study based on the datasets proves the effectiveness of our modules. The proposed CGBA-Net increased the accuracy of multiple instruments segmentation, which accurately classifies and segments the instruments. The proposed modules effectively provided instrument-related features for the network.

Emotion cause extraction (ECE) aims to extract the causes behind the certain emotion in text. Some works related to the ECE task have been published and attracted lots of attention in recent years. However, these methods neglect two major issues: 1) pay few attentions to the effect of document-level context information on ECE, and 2) lack of sufficient exploration for how to effectively use the annotated emotion clause. For the first issue, we propose a bidirectional hierarchical attention network (BHA) corresponding to the specified candidate cause clause to capture the document-level context in a structured and dynamic manner. For the second issue, we design an emotional filtering module (EF) for each layer of the graph attention network, which calculates a gate score based on the emotion clause to filter the irrelevant information. Combining the BHA and EF, the EF-BHA can dynamically aggregate the contextual information from two directions and filters irrelevant information. The experimental results demonstrate that EF-BHA achieves the competitive performances on two public datasets in different languages (Chinese and English). Moreover, we quantify the effect of context on emotion cause extraction and provide the visualization of the interactions between candidate cause clauses and contexts.

Emotion cause extraction (ECE) aims to extract the causes behind the certain emotion in text. Some works related to the ECE task have been published and attracted lots of attention in recent years. However, these methods neglect two major issues: 1) pay few attentions to the effect of document-level context information on ECE, and 2) lack of sufficient exploration for how to effectively use the annotated emotion clause. For the first issue, we propose a bidirectional hierarchical attention network (BHA) corresponding to the specified candidate cause clause to capture the document-level context in a structured and dynamic manner. For the second issue, we design an emotional filtering module (EF) for each layer of the graph attention network, which calculates a gate score based on the emotion clause to filter the irrelevant information. Combining the BHA and EF, the EF-BHA can dynamically aggregate the contextual information from two directions and filters irrelevant information. The experimental results demonstrate that EF-BHA achieves the competitive performances on two public datasets in different languages (Chinese and English). Moreover, we quantify the effect of context on emotion cause extraction and provide the visualization of the interactions between candidate cause clauses and contexts.