The oil spill detection of synthetic aperture radar (SAR) images has great success. Existing deep learning-based methods make predictions mainly based on the U-Net structure and Transformer, which fail to blend the local and global information generated by other different feature maps. In this letter, we proposed a Dual Stream Unet (DS-Unet) for oil spill detection of SAR images. Specially, the proposed DS-Unet consists of two modules, an edge feature extraction module for extracting the local information and an Inter-scale Alignment module for capturing the global information. Moreover, an edge extraction branch is applied for handling the speckle noise of SAR images. Extensive experiments on two real-world datasets (Palsar and Sentinel) have shown that the proposed DS-Unet outperforms many existing state-of-the-art methods.

Incomplete multi-view clustering becomes an important research problem, since multi-view data with missing values are ubiquitous in real-world applications. Although great efforts have been made for incomplete multi-view clustering, there are still some challenges: 1) most existing methods didn't make full use of multi-view information to deal with missing values; 2) most methods just employ the consistent information within multi-view data but ignore the complementary information; 3) For the existing incomplete multi-view clustering methods, incomplete multi-view representation learning and clustering are treated as independent processes, which leads to performance gap. In this work, we proposed a novel Incomplete Contrastive Multi-View Clustering method with high-confidence guiding (ICMVC). Firstly, we proposed a multi-view consistency relation transfer plus graph convolutional network to tackle missing values problem. Secondly, instance-level attention fusion and high-confidence guiding are proposed to exploit the complementary information while instance-level contrastive learning for latent representation is designed to employ the consistent information. Thirdly, an end-to-end framework is proposed to integrate multi-view missing values handling, multi-view representation learning and clustering assignment for joint optimization. Experiments compared with state-of-the-art approaches demonstrated the effectiveness and superiority of our method. Our code is publicly available at https://github.com/liunian-Jay/ICMVC. The version with supplementary material can be found at http://arxiv.org/abs/2312.08697.

Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than the quantity during instruction tuning of LLMs. Therefore, recently a lot of studies focus on exploring the methods of selecting high-quality subset from instruction datasets, aiming to reduce training costs and enhance the instruction-following capabilities of LLMs. This paper presents a comprehensive survey on data selection for LLM instruction tuning. Firstly, we introduce the wildly used instruction datasets. Then, we propose a new taxonomy of the data selection methods and provide a detailed introduction of recent advances, and the evaluation strategies and results of data selection methods are also elaborated in detail. Finally, we emphasize the open challenges and present new frontiers of this task.

Human activity recognition (HAR) based on sensor data is a significant problem in pervasive computing. In recent years, deep learning has become the dominating approach in this field, due to its high accuracy. However, it is difficult to make accurate identification for the activities of one individual using a model trained on data from other users. The decline on the accuracy of recognition restricts activity recognition in practice. At present, there is little research on the transferring of deep learning model in this field. This is the first time as we known, an empirical study was carried out on deep transfer learning between users with unlabeled data of target. We compared several widely-used algorithms and found that Maximum Mean Discrepancy (MMD) method is most suitable for HAR. We studied the distribution of features generated from sensor data. We improved the existing method from the aspect of features distribution with center loss and get better results. The observations and insights in this study have deepened the understanding of transfer learning in the activity recognition field and provided guidance for further research.

Mobile edge computing (MEC) makes up for the disadvantages of cloud computing, and has gained a considerable momentum recently. However, the dynamically changing QoS always results in failures of QoS-ware recommendation and composition of MEC services, which significantly negates the advantages of MEC. To address this issue, considering user-related and service-related contextual factors and various MEC services scheduling scenarios, we propose two context-aware QoS prediction schemes for MEC services. The first scheme is designed for the situations when MEC services are scheduled in real-time, which contains two context-aware real-time QoS estimation methods. One can estimate the real-time multi-QoS of MEC services and the other can estimate the real-time fitted QoS of MEC services. The second scheme is designed for the situations when MEC services are scheduled in the future. This scheme includes two context-aware QoS prediction methods. One can predict the multi-QoS of MEC services and the other can predict the fitted QoS of MEC services. Finally, adaptive QoS prediction strategies are developed in the light of characteristics of the proposed methods. According to these strategies, the most appropriate QoS prediction method could be scheduled adaptively. Extensive experiments are conducted to validate our proposed approaches and to demonstrate their performance.