In an effort to the problem of insufficient tracking performance of the Fully-convolutional Siamese network (SiamFC) in complex scenarios, a dual attention mechanism object tracking algorithm based on the Fully-convol...
详细信息
In an effort to the problem of insufficient tracking performance of the Fully-convolutional Siamese network (SiamFC) in complex scenarios, a dual attention mechanism object tracking algorithm based on the Fully-convolutional Siamese network is proposed to improve the generalization capability of the tracker by ameliorating the robustness of the template characteristics. Firstly, a global context attention module is appended after the backbone network of SiamFC to ameliorate the power of original feature extraction from two dimensions of spatial and channel. Then, a coordinate attention module is introduced to augment the capability of feature extraction in the channel dimension. Finally, the model of the proposed algorithm is trained on the Got-10k dataset. Five related algorithms are tested on the OTB2015 dataset, the results of experiments manifest that our algorithm outperforms the baseline trackers, the success and precision rate of the proposed algorithm are improved by 3.3% and 6.3%. The average tracking speed is 145FPS, which can demand the requirement of real-time tracking.
World models significantly enhance hierarchical understanding, improving data integration and learning efficiency. To explore the potential of the world model in the remote sensing (RS) field, this paper proposes a la...
详细信息
In the recommendation system, user-item preferences are described by a High-Dimensional and Sparse (HiDS) matrix. Collaborative Filtering (CF)-based models have been widely adopted to solve unknown entries estimation....
详细信息
In the recommendation system, user-item preferences are described by a High-Dimensional and Sparse (HiDS) matrix. Collaborative Filtering (CF)-based models have been widely adopted to solve unknown entries estimation. However, a CF-based model does not take the data distribution characteristic of an HiDS matrix into account, thereby its representation ability limited. To address this issue, this paper proposes to build a Siamese Generative Adversarial Predicting Network (SGAPN) to estimate the unknown entries in an HiDS matrix. Firstly, we build a model to learn the data distribution characteristic of an HiDS matrix. Secondly, based on the learned data distribution and observed entries, we build a model to estimate the unknown entries. Compared with the CF-based model, our model takes the data distribution of an HiDS matrix into account to address the unknown entries estimation. Experimental results over four HiDS matrices generated by industrial applications demonstrate that compared with several state-of-the-art models, the proposed model achieves competitive prediction accuracy.
Recent studies have shown that detectors based on deep models are vulnerable to adversarial examples, even in the black-box scenario where the attacker cannot access the model information. Most existing attack methods...
详细信息
Motivated by the need for decentralized learning, this paper aims at designing a distributed algorithm for solving nonconvex problems with general linear constraints over a multi-agent network. In the considered probl...
详细信息
Chest radiography is widely used in annual medical screening to check whether lungs are healthy or not. Therefore it would be desirable to develop an intelligent system to help clinicians automatically detect potentia...
详细信息
A recommender system (RS) commonly adopts a High-dimensional and sparse (HiDS) matrix to describe user-item preferences. Collaborative Filtering (CF)-based models have been widely adopted to address such an HiDS matri...
详细信息
ISBN:
(纸本)9781665442084
A recommender system (RS) commonly adopts a High-dimensional and sparse (HiDS) matrix to describe user-item preferences. Collaborative Filtering (CF)-based models have been widely adopted to address such an HiDS matrix. However, a CF-based model is unable to learn the property distribution characteristic of user’s preference from an HiDS matrix, thereby its representation ability is limited. To address this issue, this paper proposes a Model Regularization Wasserstein GAN(MRWGAN) to extract the distribution of user’s preferences. Its main ideas are two-fold: a) adopting an auto-encoder to implement the generator model of GAN; b) proposing a model-regularized Wasserstein distance as an objective function to training a GAN model. Empirical studies on four HiDS matrices from industrial applications demonstrate that compared with state-of-the-art models, the proposed model achieves higher prediction accuracy for missing data of an HiDS matrix.
Objective: To resolve the underestimation problem and investigate the mechanism of the AI model which employed to predict cardiovascular disease (CVD) risk scores from retinal fundus photos. Methods: An ordinal regres...
详细信息
This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge devices train and transmit quantized version...
详细信息
ISBN:
(纸本)9781665435413
This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge devices train and transmit quantized versions of their local FL model parameters to a coordinating server, which, in turn, aggregates them into a quantized global model and synchronizes the devices. With the goal of jointly determining the set of participating devices in each training iteration and the bitwidths employed at the devices, we pose an optimization problem for minimizing the training loss of quantized FL under a device sampling budget and delay requirement. Our analytical results show that the improvement of FL training loss between two consecutive iterations depends on not only the device selection and quantization scheme, but also on several parameters inherent to the model being learned. As a result, we propose, a model-based reinforcement learning (RL) method to optimize action selection over iterations. Compared to model-free RL, the proposed approach leverages the derived mathematical characterization of the FL training process to discover an effective device selection and quantization scheme without imposing additional device communication overhead. Numerical evaluations show that the proposed FL framework can achieve the same classification performance while reducing the number of training iterations needed for convergence by 20% compared to model-free RL-based FL.
—With the rapid development of technology and the acceleration of digitalisation, the frequency and complexity of cyber security threats are increasing. Traditional cybersecurity approaches, often based on static rul...
详细信息
暂无评论