检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shan, Xiangheng Wu, Dongyue Zhu, Guilin Shao, Yuanjie Sang, Nong Gao, Changxin National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish this task, they are still easily overfitting to training classes due to the natural gaps in semantic information between training and new classes. To overcome this challenge, we propose a novel framework for open-vocabulary semantic segmentation called EBSeg, incorporating an Adaptively Balanced Decoder (AdaB Decoder) and a Semantic Structure Consistency loss (SSC Loss). The AdaB Decoder is designed to generate different image embeddings for both training and new classes. Subsequently, these two types of embeddings are adaptively balanced to fully exploit their ability to recognize training classes and generalization ability for new classes. To learn a consistent semantic structure from CLIP, the SSC Loss aligns the inter-classes affinity in the image feature space with that in the text feature space of CLIP, thereby improving the generalization ability of our model. Furthermore, we employ a frozen SAM image encoder to complement the spatial information that CLIP features lack due to the low training image resolution and image-level supervision inherent in CLIP. Extensive experiments conducted across various benchmarks demonstrate that the proposed EBSeg outperforms the state-of-the-art methods. Our code and trained models will be here: https://***/slonetime/EBSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Cascaded mixed pyramid pooling for surface defect segmentation in solid oxide fuel cell 3

Cascaded mixed pyramid pooling for surface defect segmentati...

引用

3rd International Conference on Electronic Information Engineering, Big Data, and Computer technology, EIBDCT 2024

作者： Wang, Yaokun Fu, Xiaowei Li, Xi Xu, Wei College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

ISBN: (纸本)9781510680449

To address the issues of defect leakage and mis-segmentation in the surface defect segmentation of solid oxide fuel cells, we propose a cascaded mixed pyramid pooling segmentation method. In the encoding part, attention-based depth-wise separable convolution is implemented to replace the traditional convolution. This reduces the computational complexity and achieves hierarchical feature extraction. Secondly, cascaded sampling is applied to the last three layers of the encoder to promote multi-level feature fusion, and mixed pyramid pooling consisting of atrous convolution and strip pooling is adopted to achieve feature extraction for long-range band defects. Lastly, an adaptive loss function is constructed to supervise the training process, balancing the relative importance among the losses and improving the learning of defect features by the network. The experiments demonstrate that the proposed method improves segmentation accuracy, as evidenced by better results in mean absolute error, F1 score, intersection over union, and Pratt's figure of merit. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Physics-Informed Neural Network with Two-Stage Learning Strategy to Solve Partial Differential Equations

引用

Numerical Mathematics(Theory,Methods and Applications) 2023年第2期16卷 298-322页

作者： Shuyan Shi Ding Liu Ruirui Ji Yuchao Han School of Automation and Information Engineering Xi‘an University of TechnologyXi‘an 710048P.R.China National&Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi‘an 710048P.R.China Xi’an University of Technology Shannxi Key Laboratory of Complex System Control and Intelligent Information ProcessingXi‘an 710048P.R.China

Physics-Informed Neural Network(PINN)represents a new approach to solve Partial Differential Equations(PDEs).PINNs aim to solve PDEs by integrating governing equations and the initial/boundary conditions(I/BCs)into a loss ***,the imbalance of the loss function caused by parameter settings usually makes it difficult for PINNs to converge,*** they fall into local *** other words,the presence of balanced PDE loss,initial loss and boundary loss may be critical for the *** addition,existing PINNs are not able to reveal the hidden errors caused by non-convergent boundaries and conduction errors caused by the PDE near the ***,these problems have made PINN-based methods of limited use on practical *** this paper,we propose a novel physics-informed neural network,*** adaptive physics-informed neural network with a two-stage training *** algorithm adds spatio-temporal coefficient and PDE balance parameter to the loss function,and solve PDEs using a two-stage training process:pre-training and formal *** pre-training step ensures the convergence of boundary loss,whereas the formal training process completes the solution of PDE by balancing various loss *** order to verify the performance of our method,we consider the imbalanced heat conduction and Helmholtz equations often appearing in practical *** Klein-Gordon equation,which is widely used to compare performance,reveals that our method is able to reduce the hidden *** results confirm that our algorithm can effectively and accurately solve models with unbalanced loss function,hidden errors and conduction *** codes developed in this manuscript are publicy available at https://***/callmedrcom/ATPINN.

关键词： Physics informed neural networks partial differential equations two-stage learning scientific computing

来源：评论

学校读者我要写书评

暂无评论

Path Planning Method of Unmanned Surface Vessel Based on Strategy Integration 23rd

Path Planning Method of Unmanned Surface Vessel Based on Str...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and Engineering, IFToMM CCMMS 2022

作者： Yang, Caipei Zhao, Yingqi Liu, Jie Zhou, Kaibo MOE Key Laboratory of Image Information Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811993978

In the task of path planning, the unmanned surface vessels (USV) are required to reach the destination while avoiding obstacle. However, it is difficult for USV to prioritize the two sub-target tasks of destination arrival and obstacle avoidance in a complex dynamic environment using traditional path planning methods. Based on the above considerations, a path planning method for USVs based on strategy integration is proposed. Firstly, the path planning scenario containing dynamic obstacles and two sub-target scenarios are set up. In order to strengthen its ability to reach the destination and avoid dynamic obstacles, the dynamic obstacles and the destination are removed separately in the two sub-target scenarios. Furthermore, the model for strategy selection is trained on action decisions in sub-target scenarios through double deep Q-Network with prioritized experience replay. Finally, a framework for strategy integration is designed to optimize strategy selection for USV. The simulation results show that the proposed method achieves a good overall performance and a higher path planning success rate than the traditional path planning method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Entity Linking for Chinese Short Texts Based on Multi-Task Learning 3

Entity Linking for Chinese Short Texts Based on Multi-Task L...

引用

3rd International Conference on Advanced Algorithms and Neural Networks, AANN 2023

作者： Liu, Zhongge Yu, Minghui School of Artificial Intelligence and Automation Huazhong University of Science and Technology 1037 Luoyu Road HuBei WuHan430074 China National Key Laboratory of Multispectral Information Intelligent Processing Technology 1037 Luoyu Road HuBei WuHan430074 China

ISBN: (纸本)9781510668355

Entity linking task aims to establish unambiguous links between entity mentions in text and target entities in the knowledge base. Traditional entity linking models rely on complete context information in long texts. However, with the fast-growing amount of internet data, most of the data is in short text which presents a range of challenges including poor contextual semantics and disordered word order. Additionally, compared to English, Chinese poses greater challenges for entity linking task due to its unique language characteristics. To address this, we propose a multi-task learning based entity linking model for Chinese short text. By utilizing the fine-grained entity typing task as an auxiliary task for entity linking, and sharing the BERT-BiLSTM encoder, the model can leverage the implicit relationship between the two tasks to maximize potential information in the text and enhance performance in entity linking. Experimental results on Chinese short text datasets demonstrate that our proposed model outperforms a range of deep-learning based entity linking models, as well as the single-task entity linking model with the same structure, fully verifying the effectiveness of the proposed approach. © 2023 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Optimal Transport for Robust Domain Adaptation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1667-1680页

作者： Bingrong Xu Jianhua Yin Cheng Lian Yixin Su Zhigang Zeng IEEE the School of Automation Wuhan University of TechnologyWuhan 430070China Intelligent Transportation Systems Research Center Wuhan University of TechnologyWuhan 430063 Chongqing Research Institute Wuhan University of TechnologyChongqingChina the School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074 the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074China

When encountering the distribution shift between the source(training) and target(test) domains, domain adaptation attempts to adjust the classifiers to be capable of dealing with different domains. Previous domain adaptation research has achieved a lot of success both in theory and practice under the assumption that all the examples in the source domain are welllabeled and of high quality. However, the methods consistently lose robustness in noisy settings where data from the source domain have corrupted labels or features which is common in reality. Therefore, robust domain adaptation has been introduced to deal with such problems. In this paper, we attempt to solve two interrelated problems with robust domain adaptation:distribution shift across domains and sample noises of the source domain. To disentangle these challenges, an optimal transport approach with low-rank constraints is applied to guide the domain adaptation model training process to avoid noisy information influence. For the domain shift problem, the optimal transport mechanism can learn the joint data representations between the source and target domains using a measurement of discrepancy and preserve the discriminative information. The rank constraint on the transport matrix can help recover the corrupted subspace structures and eliminate the noise to some extent when dealing with corrupted source data. The solution to this relaxed and regularized optimal transport framework is a convex optimization problem that can be solved using the Augmented Lagrange Multiplier method, whose convergence can be mathematically proved. The effectiveness of the proposed method is evaluated through extensive experiments on both synthetic and real-world datasets.

关键词： Domain adaptation low-rank constraint noise corruption optimal transport

来源：评论

学校读者我要写书评

暂无评论

Chinese Event Extraction Method Based on Roformer Model

引用

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Qiang, Baohua Zhou, Xiangyu Wang, Yufeng Yang, Xianyi Wang, Yuemeng Tian, Jubo Chen, Peng Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC Shijiazhuang050081 China

Event extraction is an important research direction in the field of natural language processing. The current Chinese event extraction field still suffers from errors in the pretraining and fine-tuning stages, inability to directly handle texts with more than 512 tokens, and inaccurate event extraction due to insufficient semantic sample diversity. In this paper, we propose a Chinese event extraction method RoformerFC (Roformer model with FGM and CRF) based on the Roformer model to address the above problems. Firstly, our method utilizes the Roformer model based on rotary position embedding, which both moderates the errors in the pretraining and fine-tuning phases and allows the model to directly handle texts with more than 512 tokens;then, the adversarial networks based on FGM (fast gradient method) are realized to increase the diversity of semantic feature samples;finally, the classical CRF (conditional random fields) model is used to decode and identify the event element entity and its corresponding event role and event type. On the short text DuEE dataset, the microP, microR, and microF of our method improved 1.26%, 4.01%, and 2.68%, respectively, over the classical Chinese event extraction method BERT-CRF. On the long text JsEE dataset, the microP, microR, and microF of our method improved 2.26%, 5.03%, and 3.72%, respectively, over the classical Chinese event extraction method BERT-CRF. © 2023 Baohua Qiang et al.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Bi-Temporal Feature Relational Distillation for On-Board Lightweight Change Detection in Remote Sensing Imagery

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Wang, Guoqing Chen, He Li, Jie Wang, Jue Liu, Wenchao Chen, Liang Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China Shanghai Aerospace Electronic Technology Institute Shanghai201109 China

Deep learning models for remote sensing change detection (CD) require significant resources, challenging real-time applications on spaceborne devices. Knowledge distillation (KD) technology is a potential solution that balances model size and CD performance. However, existing KD methods struggle to effectively transfer the teacher's ability to respond to changed landcovers, and also face challenges in assisting the student model in detecting changes in landcovers with subtle visual characteristics. To overcome these limitations, a bi-temporal feature relational distillation (FRD) framework is proposed. The FRD framework includes two designed distillation components: bi-temporal feature distance distillation (BFDD) and contrastive cluster representation distillation (CCRD). BFDD guides the student model to learn the relationship between bi-temporal feature categories from the teacher model and introduces the iteration-wise random selection and bilinear interpolation strategy to solve feature mismatch problem between the teacher and the student. CCRD describes the pixel-level and clusterlevel feature distributions through the designed contrastive cluster (CC) module, guiding the student model to align the change/nonchange features with the teacher model, so as to alleviate the confusion of change/non-change features. Extensive experiments and analyses have confirmed that the proposed FRD framework can develop lightweight models capable of achieving performance comparable to large models, thereby enhancing suitability for realtime CD. © 1965-2011 IEEE.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

Improving the Robustness of Low-Resource Neural Machine Translation with Adversarial Examples 1

引用

18th China Conference on Machine Translation, CCMT 2022

作者： Sun, Shuo Hou, Hongxu Wu, Nier Yang, Zongheng Wang, Yisong Wang, Pengcong Jian, Weichen Inner Mongolia Key Laboratory of Mongolian Information Processing Technology National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian College of Computer Science Inner Mongolia University Hohhot China

ISBN: (数字)9789811979606

ISBN: (纸本)9789811979590

Weak robustness and noise adaptability are major issues for Low-Resource Neural Machine Translation (NMT) models. That is, once some tiny perturbs are added to the input sentence, the model will produce completely different translation with high confidence. Adversarial example is currently a major tool to improve model robustness and how to generate an adversarial examples that can degrade the performance of the model and ensure semantic consistency is a challenging task. In this paper, we adopt reinforcement learning to generate adversarial example for low-resource NMT. Specifically, utilizing the actor-critic algorithm to modify the source sentence, the discriminator and translation model in the environment are used to determine whether the generated adversarial examples maintain semantic consistency and the overall deterioration of the model. Furthermore, we also install a language model reward to measure the fluency of adversarial examples. Experimental results on low-resource translation tasks show that our method highly aggressive to the model while maintaining semantic constraints greatly. Moreover, the model performance is significantly improved after fine-tuning with adversarial examples. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Edible prodelphinidins that improve postprandial hyperglycemia were discovered in Chinese bayberry(Myrica rubra *** Zucc.)fruits

引用

Food Science and Human Wellness 2025年第3期14卷 1008-1016页

作者： Yi Wang Laiming Zhang Jiaxiong Wu Chengxiao Yu Xingqian Ye Haibo Pan Shiguo Chen College of Biosystems Engineering and Food Science National-Local Joint Engineering Laboratory of Intelligent Food Technology and EquipmentZhejiang Key Laboratory for Agro-food ProcessingIntegrated Research Base of Southern Fruit and Vegetable Preservation TechnologyZhejiang International Scientific and Technological Cooperation Base of Health Food Manufacturing and Quality ControlZhejiang UniversityHangzhou 310058China Ningbo Research Institute Zhejiang UniversityNingbo 315100China Zhejiang University Zhongyuan Institute Zhengzhou 450000China Innovation Center of Yangtze River Delta Zhejiang UniversityJiaxing 314102China

Plant polyphenols are potential substitutes for clinicalα-glucosidase *** previous studies indicated that prodelphinidins from Chinese bayberry leaves(BLPs)have strongerα-glucosidase inhibitory activity than other common polyphenols,but they have no safe history of *** is a reasonable prospect that prodelphinidins from Chinese bayberry fruits(BFPs)can improve postprandial hyperglycemia,though known active components are only myricetin and ***,the aim of this study was to analyze structure and hypoglycemic effect of BFPs of“Biqi”(BQPs)and“Dongkui”(DKPs)cultivars,and compare their difference with *** contents of BQPs and DKPs were(221.73±0.60)and(136.82±4.33)mg epicatechin(EC)equivalents/g dry weight,*** most subunits were epigallocatechin gallate along with a small amount of epigallocatechin,epicatechin gallate and EC connected by B-type linkages and a small portion of A-type linkages with mean polymerization degree of 4.25 and 4.08,***,BQPs and DKPs wereα-glucosidase inhibitors with half inhibitory concentration of 11.91 and 9.47μg/m L respectively,which were significantly stronger than *** could also improve postprandial hyperglycemia of normal mice and high fat diet-induced type II diabetic ***,edible prodelphinidins,which have stronger hypoglycemic effect than BLPs,were first found in Chinese bayberry fruits.

关键词： Chinese bayberry fruit Prodelphinidins Structure α-Glucosidase Postprandial hyperglycemia

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：