检索结果-内蒙古大学图书馆

Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filtering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Bing Li, Ximing Yang, Zhiyao Guan, Yuanyuan Li, Jiayin Wang, Shengsheng College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China School of Humanities Jilin University China

Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic embedding space, where the embeddings of high-frequency words are clustered but those of low-frequency words disperse sparsely. This anisotropic phenomenon results in two problems of similarity bias and information bias, lowering the quality of sentence embeddings. To solve the problems, we fine-tune PLMs by leveraging the frequency information of words and propose a novel USRL framework, namely Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering (SLT-FAI). We calculate the word frequencies over the pre-training corpora of PLMs and assign words thresholding frequency labels. With them, (1) we incorporate a similarity discriminator used to distinguish the embeddings of high-frequency and low-frequency words, and adversarially tune the PLM with it, enabling to achieve uniformly frequency-invariant embedding space;and (2) we propose a novel incomplete sentence detection task, where we incorporate an information discriminator to distinguish the embeddings of original sentences and incomplete sentences by randomly masking several low-frequency words, enabling to emphasize the more informative low-frequency words. Our SLT-FAI is a flexible and plug-and-play framework, and it can be integrated with existing USRL techniques. We evaluate SLT-FAI with various backbones on benchmark datasets. Empirical results indicate that SLT-FAI can be superior to the existing USRL baselines. Our code is released in https://***/wangbing1416/SLT-FAI. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

Geometrical Characterizations of Non-Radiating Sources at Polyhedral and Conical Corners with Applications

学校读者我要写书评

暂无评论

Communications in Mathematical Research 2023年第4期39卷 523-538页

作者： Huaian Diao Yueran Geng Hongyu Liu Qinghua Yu School of Mathematics and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchunJilin 130012P.R.China. Department of Mathematics City University of Hong KongKowloonHong Kong SARP.R.China. The School Attached to Dalian Maritime University Dalian 116000P.R.China.

Considering the acoustic source scattering problems,when the sour-ce is non-radiating/invisible,we investigate the geometrical characterization for the underlying sources at polyhedral and conical *** is revealed that the non-radiating source with Holder continuous regularity must vanish at the *** this kind of geometrical characterization of non-radiating sources,we establish local and global unique determination for a source with the polyhedral or corona shape support by a single far field *** by a single far field measurement constitutes of a long standing problem in inverse scattering problems.

关键词： Non-radiating sources corner singularity vanishing inverse scattering sin-gle far-field measurement

Research on Liver Segmentation of CT Image Based on Deep Active Contour Model 3

学校读者我要写书评

暂无评论

Research on Liver Segmentation of CT Image Based on Deep Act...

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer engineering and Applications, CVIDL and ICCEA 2022

作者： He, Shanshan Song, Jinfang Zhang, Yonggang Tian, Xin Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun China Jilin University College of Software Changchun China Second Hospital of Jilin University Department of Pediatrics Changchun China Jilin University College of Computer Science and Technology Changchun China

ISBN: (纸本)9781665459112

Liver cancer is one of the liver diseases with a high morbidity and mortality. At present, surgery is still the main treatment method for liver cancer. Therefore, it is particularly important to accurately segment the liver on CT imaging. Deep learning-based algorithms struggle to derive shape priors due to the irregular shape of the liver and blurring organ borders in CT images. We present a two-stage 3D deep active contour model 3DAC based on the V-net and CV models, in which the neural network is guided to learn the global features by regressing the signed distance map. The signed distance function can also be used as an initialization level set function. Then, the active contour model is extended to three dimensions to enable evolution of the overall liver surface. The advantages of the proposed method for liver segmentation were validated on the AbdomenCT-lK dataset. Compared with the DALS method, the Dice coefficient and the Jaccard coefficient are improved by 4.29% and 4.58%, the ASD and 95HD indicators are improved by 5. 96mm and 10. 04mm, which proves the effectiveness and robustness of the proposed method. © 2022 IEEE.

关键词： Image segmentation

Low-altitude Friendly-Jamming for Satellite-Maritime Communications via Generative AI-enabled Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Jiawei Wang, Aimin Sun, Geng Li, Jiahui Wang, Jiacheng Niyato, Dusit Leung, Victor C.M. College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518115 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering The University of British Columbia VancouverV6T 1Z4 Canada

Low Earth Orbit (LEO) satellites can be used to assist maritime wireless communications for data transmission across wide-ranging areas. However, extensive coverage of LEO satellites, combined with openness of channels, can cause the communication process to suffer from security risks. This paper presents a low-altitude friendly-jamming LEO satellite-maritime communication system enabled by a unmanned aerial vehicle (UAV) to ensure data security at the physical layer. Since such a system requires trade-off policies that balance the secrecy rate and energy consumption of the UAV to meet evolving scenario demands, we formulate a secure satellite-maritime communication multi-objective optimization problem (SSMCMOP). In order to solve the dynamic and long-term optimization problem, we reformulate it into a Markov decision process. We then propose a transformer-enhanced soft actor critic (TransSAC) algorithm, which is a generative artificial intelligence-enable deep reinforcement learning approach to solve the reformulated problem, so that capturing global dependencies and diversely exploring weights. Simulation results demonstrate that the TransSAC outperforms various baselines, and achieves an optimal secrecy rate while effectively minimizing the energy consumption of the UAV. Moreover, the results find more suitable constraint values for the system. Copyright © 2025, The Authors. All rights reserved.

关键词： Multiobjective optimization

Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Bing Luo, Wei Li, Gang Huang, Jing Yang, Bo College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China School of Information Technology Deakin University Geelong Australia

As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks. Strongly influenced by graph neural networks, latent vertex embeddings are naturally adopted in many neural dynamical network models. However, we show that embeddings tend to induce a model that fits observations well but simultaneously has incorrect dynamical behaviours. Recognising that previous studies narrowly focus on short-term predictions during the transient phase of a flow, we propose three tests for correct long-term behaviour, and illustrate how an embedding-based dynamical model fails these tests, and analyse the causes, particularly through the lens of topological conjugacy. In doing so, we show that the difficulties can be avoided by not using embedding. We propose a simple embedding-free alternative based on parametrising two additive vector-field components. Through extensive experiments, we verify that the proposed model can reliably recover a broad class of dynamics on different network topologies from time series data. © 2023, CC BY.

关键词： Dynamical systems

Dual UAV Cluster-Assisted Maritime Physical Layer Secure Communications via Collaborative Beamforming

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Huang, Jiawei Wang, Aimin Sun, Geng Li, Jiahui Wang, Jiacheng Du, Hongyang Niyato, Dusit College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering Hong Kong University 999077 Hong Kong

Unmanned aerial vehicles (UAVs) can be utilized as relay platforms to assist maritime wireless communications. However, complex channels and multipath effects at sea can adversely affect the quality of UAV transmitted signals. Collaborative beamforming (CB) can enhance the signal strength and range to assist the UAV relay for remote maritime communications. However, due to the open nature of UAV channels, security issue requires special consideration. This paper proposes a dual UAV cluster-assisted system via CB to achieve physical layer security in maritime wireless communications. Specifically, one UAV cluster forms a maritime UAV-enabled virtual antenna array (MUVAA) relay to forward data signals to the remote legitimate vessel, and the other UAV cluster forms an MUVAA jammer to send jamming signals to the remote eavesdropper. In this system, we formulate a secure and energy-efficient maritime communication multi-objective optimization problem (SEMCMOP) to maximize the signal-to-interference-plus-noise ratio (SINR) of the legitimate vessel, minimize the SINR of the eavesdropping vessel and minimize the total flight energy consumption of UAVs. Since the SEMCMOP is an NP-hard and large-scale optimization problem, we propose an improved swarm intelligence optimization algorithm with chaotic solution initialization and hybrid solution update strategies to solve the problem. Simulation results indicate that the proposed algorithm outperforms other comparison algorithms, and it can achieve more efficient signal transmission by using the CB-based method. Copyright © 2024, The Authors. All rights reserved.

关键词： Multiobjective optimization

Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers

学校读者我要写书评

暂无评论

Beyond Attentive Tokens: Incorporating Token Importance and ...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sifan Long Zhen Zhao Jimin Pi Shengsheng Wang Jingdong Wang College of Computer Science and Technology Jilin University Jilin China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin China Baidu VIS University of Sydney

Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant tokens for efficient vision transformers recently. However, existing studies mainly focus on the token importance to preserve local attentive tokens but completely ignore the global token diversity. In this paper, we emphasize the cruciality of diverse global semantics and propose an efficient token decoupling and merging method that can jointly consider the token importance and diversity for token pruning. According to the class token attention, we decouple the attentive and inattentive tokens. In addition to preserving the most discriminative local tokens, we merge similar inattentive tokens and match homogeneous attentive tokens to maximize the token diversity. Despite its simplicity, our method obtains a promising trade-off between model complexity and classification accuracy. On DeiT-S, our method reduces the FLOPs by 35% with only a 0.2% accuracy drop. Notably, benefiting from maintaining the token diversity, our method can even improve the accuracy of DeiT-T by 0.1% after reducing its FLOPs by 40%.

关键词：

Research on Liver Fat Sequencing Measurement Method Combined with Super-pixel Segmentation 3

学校读者我要写书评

暂无评论

Research on Liver Fat Sequencing Measurement Method Combined...

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer engineering and Applications, CVIDL and ICCEA 2022

作者： Jiao, Xu Song, Jinfang Zhang, Yonggang Tian, Xin Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China Jilin University College of Software Changchun China Second Hospital of Jilin University Department of Pediatrics Changchun China Jilin University College of Computer Science and Technology Changchun China

ISBN: (纸本)9781665459112

The number of patients with nonalcoholic fatty liver is increasing. Liver fat quantification is the most reliable indicator for the diagnosis of non-alcoholic fatty liver disease, and it is of great value for the early diagnosis and condition monitoring of non-alcoholic fatty liver disease. Therefore, it is of great significance to quantitatively analyze liver fat. In this work, we utilize the superpixel segmentation method based on depth neural network to preprocess the MRI image, we can simplify the representation of the image and obtain good organ boundary information. In addition, we also understand the popular involution operator and improve it through combining the medical image segmentation model u-net to obtain a better region of interest. The segmentation accuracy of the proposed method is 1.82 percentage points higher than that of u-net model. On this basis, the proton density and fat fraction of liver are calculated by medical formula, achieving the sequencing measurement of liver fat. The experimental results show that the proposed method is efficient and feasible. © 2022 IEEE.

关键词： Magnetic resonance imaging

An Improved Pigeon-Inspired Optimization for Multi-focus Noisy Image Fusion

学校读者我要写书评

暂无评论

Journal of Bionic engineering 2021年第6期18卷 1452-1462页

作者： Yingda Lyu Yunqi Zhang Haipeng Chen Public Computer Education and Research Center Jilin UniversityChangchun130012China College of Software Jilin UniversityChangchun 130012China College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China

Image fusion technology is the basis of computer vision task,but information is easily affected by noise during *** this paper,an Improved Pigeon-Inspired Optimization(IPIO)is proposed,and used for multi-focus noisy image fusion by combining with the boundary handling of the convolutional sparse *** two-scale image decomposition,the input image is decomposed into base layer and detail *** the base layer,IPIO algorithm is used to obtain the optimized weights for fusion,whose value range is gained by fusing the edge ***,the global information entropy is used as the fitness index of the IPIO,which has high efficiency especially for discrete optimization *** the detail layer,the fusion of its coefficients is completed by performing boundary processing when solving the convolution sparse representation in the frequency *** sum of the above base and detail layers is as the final fused *** results show that the proposed algorithm has a better fusion effect compared with the recent algorithms.

关键词： Improved pigeon-inspired optimization Convolutional sparse representation Noisy image fusion Bionic algorithm