In the saliency object detection task, a salient object detection method based on object integrity enhancement guided edge information is proposed to address the problems of blurred edges and object incompleteness in recognition results. Firstly, the diversity feature extraction module was proposed to capture the features of complex and variable salient objects through various convolutional operations, thereby enriching the feature representation of the model. Then, the object integrity enhancement module was designed to process the initial fused multi-level features in parallel, and the integrity information of salient objects was further enhanced by exploring spatial and channel branches. Finally, the edge feature enhancement module was employed to use the deep edge prediction features to guide the feature map to pay more attention to the foreground and background region and edge information, and to improve the model’s edge perception capability. Experiments on four public datasets, such as ECSSD and DUTS-TE, showed that the proposed algorithm achieved higher detection accuracy than other advanced algorithms in several metrics, such as S-measure and F-measure on DUTS-TE dataset were 0.859 and 0.895, respectively. The proposed algorithm demonstrated superior capability in the perception and refinement of salient object boundaries, further enhancing its robustness in complex scenes.

With the improvement of people’s quality of life, the requirements for service quality have become higher. The judgment of merchants on users' reviews has been improved from good or bad to specific aspects, while traditional sentiment classification is difficult to complete this task, where sentiment word extraction of text is the key. Most of the existing models use segmented subtasks for training. In order to solve the problem of model error propagation in multiple subtasks and improve the deep learning of data, an aspect sentiment analysis model based on interactive grid tagging scheme of bidirectional encoder representation from transformers (BERT) (IGTS-BERT) was proposed. Firstly, the rotation position encoding was used to enhance the model’ s sensitivity to position, and the word pairs were labeled with a low-dimensional method to improve the learning efficiency. Then, the two grid tagging networks based on the rotational position were made to interact, giving the model a better generalization ability. Finally, in order to further exert the effect of interacting, two data augmentation methods were proposed: splicing method and a method about random matching of aspect words and sentiment words, which further improves the performance of the model. The Triplets extraction and Pairs extraction tasks were tested on 4 standard datasets, with an average improvement of more than 4% in F1 value and a maximum improvement of 7%. Experimental results show that the IGTS-BERT model exhibits superior performance on sentiment word extraction.

The diversity of individuals affects the quality of the solution sets and determines the distribution of the solution sets in solving multi-objective optimization problems. In order to expand the search direction of individuals, increase the diversity of the population and avoid individuals from gathering at the boundary during the mutation process, a chaotic opposition initialization and average mutation update-based differential evolution (COI-AMU_DE) is proposed. Firstly, in order to generate a uniformly distributed initial population, random numbers are subjected to tent chaotic map and opposition-based learning in the initialization process to generate uniformly distributed random numbers. Secondly, a mutation operator is processed to avoid individuals from gathering at the boundary to improve the diversity of population. In each iteration, the average mutation update of the individuals is carried out for legalization, and the weighted sum of the rankings based on the Pareto dominance and the constrained dominance principle (CDP) are calculated. Then the next generation of individuals is selected according to the weighted sum sorting, and the process is repeated until the end condition is satisfied to obtain the result sets. Finally, a total of 38 multi-objective optimization problems in three test suites are selected to evaluate the performance of the proposed algorithm, and it is compared with seven algorithms. The simulation results show that COI-AMU_DE has high comprehensive performance in solving constrained multi-objective optimization problems.

The convolutional neural network (CNN) method based on DeepLabv3+ has some problems in the semantic segmentation task of high-resolution remote sensing images, such as fixed receiving field size of feature extraction, lack of semantic information, high decoder magnification, and insufficient detail retention ability. A hierarchical feature fusion network (HFFNet) was proposed. Firstly, a combination of transformer and CNN architectures was employed for feature extraction from images of varying resolutions. The extracted features were processed independently. Subsequently, the features from the transformer and CNN were fused under the guidance of features from different sources. This fusion process assisted in restoring information more comprehensively during the decoding stage. Furthermore, a spatial channel attention module was designed in the final stage of decoding to refine features and reduce the semantic gap between shallow CNN features and deep decoder features. The experimental results showed that HFFNet had superior performance on UAVid, LoveDA, Potsdam, and Vaihingen datasets, and its cross-linking index was better than DeepLabv3+ and other competing methods, showing strong generalization ability.

Aiming at the lack of semantic correlation between the parameters of expectation maximization attention(EMA) algorithm and images and the lack of attention to inter-channel information, a dual attention network EMA+ algorithm was proposed. Two modules were designed: spatial attention module and channel attention module. The EMA algorithm was used as the main structure by the spatial attention module. In the responsibility estimation step, the feature map itself was used as the initial parameter in the expectation maximization(EM) algorithm, and the semantic association between the parameter and the feature map was increased. Efficient channel attention(ECA) was used in the channel attention module by using one-dimensional convolution to learn the interactive information between channels. It avoided breaking the direct correspondence between channels and their weights due to dimensionality reduction operations. EMA+ significantly improved semantic segmentation tasks’ performance by fusing spatial attention modules and channel attention modules. The experimental results showed that EMA+ has achieved better intersection-over-union than EMANet and other methods on PASCAL VOC 2012 and some more complex datasets, and had better generalization ability.

The existing multi-view subspace clustering algorithms based on tensor singular value decomposition (t-SVD) predominantly utilize tensor nuclear norm to explore the intra view correlation between views of the same samples, while neglecting the correlation among the samples within different views. Moreover, the tensor nuclear norm is not fully considered as a convex approximation of the tensor rank function. Treating different singular values equally may result in suboptimal tensor representation. A hypergraph regularized multi-view subspace clustering algorithm with dual tensor log-determinant (HRMSC-DTL) was proposed. The algorithm used subspace learning in each view to learn a specific set of affinity matrices, and introduced a non-convex tensor log-determinant function to replace the tensor nuclear norm to better improve global low-rankness. It also introduced hyper-Laplacian regularization to preserve the local geometric structure embedded in the high-dimensional space. Furthermore, it rotated the original tensor and incorporated a dual tensor mechanism to fully exploit the intra view correlation of the original tensor and the inter view correlation of the rotated tensor. At the same time, an alternating direction of multipliers method (ADMM) was also designed to solve non-convex optimization model. Experimental evaluations on seven widely used datasets, along with comparisons to several state-of-the-art algorithms, demonstrated the superiority and effectiveness of the HRMSC-DTL algorithm in terms of clustering performance.