检索结果-内蒙古大学图书馆

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2045-2058页

作者： Yiming Zhang Xuenan Xu Ruoyi Du Haohe Liu Yuan Dong Zheng-Hua Tan Wenwu Wang Zhanyu Ma Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K. Department of Electronic Systems Aalborg University Aalborg Denmark

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test set from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, and this issue has received little attention. To address these issues, we propose a new zero-shot method for audio captioning. Our method is built on the contrastive language-audio pre-training (CLAP) model. During training, the model reconstructs the ground-truth caption using the CLAP text encoder. In the inference stage, the model generates text descriptions from the CLAP audio embeddings of given audio inputs. To enhance the ability of the model in transitioning from text-to-text generation to audio-to-text generation, we propose to use the mixed-augmentations-based soft prompt to learn more robust latent representations, leveraging instance replacement and embedding augmentation. Additionally, we introduce the retrieval-based acoustic-aware hard prompt to improve the cross-domain performance of the model by employing the domain-agnostic label information of sound events. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

关键词： Training Decoding Semantics Data models Acoustics Electronic mail Benchmark testing Transformers Robustness Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

Confidence Estimation Based on the Explanations of Model’s Predictions

Confidence Estimation Based on the Explanations of Model’s ...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Kaiyue Wu Changwu Huang Xin Yao Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China

Estimating the confidence of a machine learning (ML) model plays an important role in minimizing undesirable outcomes and safety risks when using ML models in the real world, especially in high-stake application scenarios. However, the majority of existing confidence estimation methods do not work well without incorporating internal information from the model, such as the gradients, internal representations or checkpoints of its training process, which might compromise the security of the model. To alleviate such limitations, we intend to design a reliable confidence estimation method that requires as little internal model information as possible, yet precisely detecting uncertain samples for the model. In this work, we propose a confidence estimation approach that learns the confidence criterion (that is, the true class probability, TCP) based on the explanations of model’s predictions. The proposed approach utilizes the knowledge learned in the model with the leverage of the explanations for model’s prediction rather than directly extracting internal information of the model, so that it can be adopted in a wide range of applications. Several experiments, including experiments on different datasets, different models and non-IID (independent and identically distributed) test datasets, are conducted to examine the effectiveness of our confidence estimation method. The experimental results show that our proposed approach provides a reliable confidence estimation and generally performs better than the compared methods, especially in the capability of recognizing when a ML model makes errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning

arXiv

引用

arXiv 2024年

作者： Jin, Chunzhen Huang, Yongfeng Wang, Yaqi Cao, Peng Zaiane, Osmar Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China Amii University of Alberta EdmontonAB Canada

Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning (SETTP) for effective style transfer in low-resource scenarios. First, SETTP learns source style-level prompts containing fundamental style characteristics from high-resource style transfer. During training, the source style-level prompts are transferred through an attention module to derive a target style-level prompt for beneficial knowledge provision in low-resource style transfer. Additionally, we propose instance-level prompts obtained by clustering the target resources based on the semantic content to reduce semantic bias. We also propose an automated evaluation approach of style similarity based on alignment with human evaluations using ChatGPT-4. Our experiments across three resourceful styles show that SETTP requires only 1/20th of the data volume to achieve performance comparable to state-of-the-art (SOTA) methods. In tasks involving scarce data like writing style and role style, SETTP outperforms previous methods by 16.24%. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Feature Attribution Explanation to Detect Harmful Dataset Shift

Feature Attribution Explanation to Detect Harmful Dataset Sh...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ziming Wang Changwu Huang Xin Yao Research Institute of Trustworthy Autonomous Systems (RITAS) Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Detecting whether a distribution shift has occurred in the dataset is a critical aspect when implementing machine learning models, as even a small shift in the data distribution may largely affect the performance of a machine learning model and thus cause the deployed model to fail. In this work, we focus on detecting harmful dataset shifts, i.e., shifts that are detrimental to the performance of the machine learning model. The existing methods usually detect whether there is a shift between two datasets according to the following framework: first carrying out dimensionality reduction on the datasets, then determining whether dataset shift exists according to the two-sample statistical test(s) on the reduced datasets. The knowledge contained in the model trained on the dataset is not utilized in the above described dataset shift detection framework. To address this, this paper proposes to take advantage of explainable artificial intelligence (XAI) techniques to exploit the knowledge in trained models when detecting harmful dataset shifts. Specifically, we employ the feature attribution explanation (FAE) method to capture the knowledge in the model and combine it with a widely-used two-sample test method, i.e., maximum mean difference (MMD), to detect harmful dataset shifts. The experimental results on more than twenty different shifts in three widely used image datasets demonstrate that the proposed method is more effective in identifying harmful dataset shifts than existing methods. Moreover, experiments on several different models show that the method is robust and effective over different models, i.e., its detection performance is not sensitive to the model used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HyperDiff: Masked Diffusion Model with High-efficient Transformer for Hyperspectral Image Cross-Scene Classification

HyperDiff: Masked Diffusion Model with High-efficient Transf...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Pei Zhang Dong Wang Chanyue Wu Jing Yang Lei Kang Zongwen Bai Ying Li Qiang Shen School of Computer Science Northwestern Polytechnical University Xi’an China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan’an University Yan’an China School of Automation and Software Engineering Shanxi University Taiyuan China Qingdao Topscomm Communication Co. Ltd Qingdao China Department of Computer Science Aberystwyth University UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of HSI representations remains limited, mainly due to class label imbalance. This paper introduces a dual-stage learning framework based on transfer learning to enhance classification accuracy in the TD. The framework includes a self-supervised learning stage and a supervised fine-tuning stage. The self-supervised stage focuses on learning robust representations by leveraging inherent structures within HSI data, while the fine-tuning stage uses training labels to extract semantic information. A masked diffusion model predicts masked tokens from unmasked ones, capturing both high-level structures and fine details in HSI data. An efficient spatiospectral Transformer, which removes self-attention from the decoder, is proposed to enhance the self-supervised process. This design allows mask tokens to obtain information from visible tokens without interacting with each other, reducing sequence length and computational costs. By decoding each mask token conditionally independently, only a subset of masked tokens is processed. Extensive experiments on two public HSI datasets demonstrate that the proposed method outperforms state-of-the-art techniques.

关键词： Training Transfer learning Self-supervised learning Transformers Diffusion models Real-time systems Decoding Computational efficiency Speech processing Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Evolving Constrained Reinforcement Learning Policy

Evolving Constrained Reinforcement Learning Policy

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Chengpeng Hu Jiyuan Pei Jialin Liu Xin Yao Research Institute of Trustworthy Autonomous Systems (RITAS) Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improves the exploration efficiency. However, when adapting this approach to address constrained problems, balancing the trade-off between the reward and constraint violation is hard. In this paper, we propose a novel evolutionary constrained reinforcement learning (ECRL) algorithm, which adaptively balances the reward and constraint violation with stochastic ranking, and at the same time, restricts the policy's behaviour by maintaining a set of Lagrange relaxation coefficients with a constraint buffer. Extensive experiments on robotic control benchmarks show that our ECRL achieves outstanding performance compared to state-of-the-art algorithms. Ablation analysis shows the benefits of introducing stochastic ranking and constraint buffer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation systems: Survey, Taxonomy and Performance Evaluation

arXiv

引用

arXiv 2024年

作者： Shahin, Nada Ismail, Leila Intelligent Distributed Computing and Systems Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Emirates Center for Mobility Research United Arab Emirates University Abu Dhabi United Arab Emirates

With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end translation system, from sign to gloss to text and vice-versa. There has been a wealth of research on machine translations and related reviews. However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. We also present the requirements of a real-time Quality-of-Service sign language machine translation system underpinned by accurate deep learning algorithms. We propose future research directions for sign language translation *** Codes I.2, I.2.7, I.4, I.4.9 © 2024, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Tackling Noisy Labels with Network Parameter Additive Decomposition

arXiv

引用

arXiv 2024年

作者： Wang, Jingyi Xia, Xiaobo Lan, Long Wu, Xinghao Yu, Jun Yang, Wenjing Han, Bo Liu, Tongliang The Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Changsha410073 China The Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering University of Sydney DarlingtonNSW2008 Australia The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Department of Automation University of Science and Technology of China Hefei230026 China The Department of Computer Science Hong Kong Baptist University Hong Kong

Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the ability to memorize all noisy data, they would first memorize clean training data, and then gradually memorize mislabeled training data. A simple and effective method that exploits the memorization effect to combat noisy labels is early stopping. However, early stopping cannot distinguish the memorization of clean data and mislabeled data, resulting in the network still inevitably overfitting mislabeled data in the early training stage. In this paper, to decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, we perform additive decomposition on network parameters. Namely, all parameters are additively decomposed into two groups, i.e. , parameters w are decomposed as w = σ + γ. Afterward, the parameters σ are considered to memorize clean data, while the parameters γ are considered to memorize mislabeled data. Benefiting from the memorization effect, the updates of the parameters σ are encouraged to fully memorize clean data in early training, and then discouraged with the increase of training epochs to reduce interference of mislabeled data. The updates of the parameters γ are the opposite. In testing, only the parameters σ are employed to enhance generalization. Extensive experiments on both simulated and real-world benchmarks confirm the superior performance of our method. The implementation is available at: https://***/wangjingyi9924/TNLPAD. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Technology Roadmap for Flexible Sensors

引用

ACS NANO 2023年第6期17卷 5211-5295页

作者： Luo, Yifei Abidian, Mohammad Reza Ahn, Jong-Hyun Akinwande, Deji Andrews, Anne M. Antonietti, Markus Bao, Zhenan Berggren, Magnus Berkey, Christopher A. Bettinger, Christopher John Chen, Jun Chen, Peng Cheng, Wenlong Cheng, Xu Choi, Seon-Jin Chortos, Alex Dagdeviren, Canan Dauskardt, Reinhold H. Di, Chong-an Dickey, Michael D. Duan, Xiangfeng Facchetti, Antonio Fan, Zhiyong Fang, Yin Feng, Jianyou Feng, Xue Gao, Huajian Gao, Wei Gong, Xiwen Guo, Chuan Fei Guo, Xiaojun Hartel, Martin C. He, Zihan Ho, John S. Hu, Youfan Huang, Qiyao Huang, Yu Huo, Fengwei Hussain, Muhammad M. Javey, Ali Jeong, Unyong Jiang, Chen Jiang, Xingyu Kang, Jiheong Karnaushenko, Daniil Khademhosseini, Ali Kim, Dae-Hyeong Kim, Il-Doo Kireev, Dmitry Kong, Lingxuan Lee, Chengkuo Lee, Nae-Eung Lee, Pooi See Lee, Tae-Woo Li, Fengyu Li, Jinxing Liang, Cuiyuan Lim, Chwee Teck Lin, Yuanjing Lipomi, Darren J. Liu, Jia Liu, Kai Liu, Nan Liu, Ren Liu, Yuxin Liu, Yuxuan Liu, Zhiyuan Liu, Zhuangjian Loh, Xian Jun Lu, Nanshu Lv, Zhisheng Magdassi, Shlomo Malliaras, George G. Matsuhisa, Naoji Nathan, Arokia Niu, Simiao Pan, Jieming Pang, Changhyun Pei, Qibing Peng, Huisheng Qi, Dianpeng Ren, Huaying Rogers, John A. Rowe, Aaron Schmidt, Oliver G. Sekitani, Tsuyoshi Seo, Dae-Gyo Shen, Guozhen Sheng, Xing Shi, Qiongfeng Someya, Takao Song, Yanlin Stavrinidou, Eleni Su, Meng Sun, Xuemei Takei, Kuniharu Tao, Xiao-Ming Tee, Benjamin C. K. Thean, Aaron Voon-Yew Trung, Tran Quang Wan, Changjin Wang, Huiliang Wang, Joseph Wang, Ming Wang, Sihong Wang, Ting Wang, Zhong Lin Weiss, Paul S. Wen, Hanqi Xu, Sheng Xu, Tailin Yan, Hongping Yan, Xuzhou Yang, Hui Yang, Le Yang, Shuaijian Yin, Lan Yu, Cunjiang Yu, Guihua Yu, Jing Yu, Shu-Hong Yu, Xinge Zamburg, Evgeny Zhang, Haixia Zhang, Xiangyu Zhang, Xiaosheng Zhang, Xueji Zhang, Yihui Zhang, Yu Zhao, Siyuan Zhao, Xuanhe Zheng, Yuanjin Zheng, Yu-Qing Zheng, Zijian Zhou, Tao Zhu, Bowen Zhu, Ming Zhu, Rong Zhu, Yangzhi Zhu, Yong Zou, Guijin Chen, Xiaodong 08-03 Innovis Singapore 138634 Republic of Singapore Innovative Centre for Flexible Devices (iFLEX) School of Materials Science and Engineering Nanyang Technological University Singapore 639798 Singapore Department of Biomedical Engineering University of Houston Houston Texas 77024 United States School of Electrical and Electronic Engineering Yonsei University Seoul 03722 Republic of Korea Department of Electrical and Computer Engineering The University of Texas at Austin Austin Texas 78712 United States Microelectronics Research Center The University of Texas at Austin Austin Texas 78758 United States Department of Chemistry and Biochemistry California NanoSystems Institute and Department of Psychiatry and Biobehavioral Sciences Semel Institute for Neuroscience and Human Behavior and Hatos Center for Neuropharmacology University of California Los Angeles Los Angeles California 90095 United States Colloid Chemistry Department Max Planck Institute of Colloids and Interfaces 14476 Potsdam Germany Department of Chemical Engineering Stanford University Stanford California 94305 United States Laboratory of Organic Electronics Department of Science and Technology Campus Norrköping Linköping University 83 Linköping Sweden Wallenberg Initiative Materials Science for Sustainability (WISE) and Wallenberg Wood Science Center (WWSC) SE-100 44 Stockholm Sweden Department of Materials Science and Engineering Stanford University Stanford California 94301 United States Department of Biomedical Engineering and Department of Materials Science and Engineering Carnegie Mellon University Pittsburgh Pennsylvania 15213 United States Department of Bioengineering University of California Los Angeles Los Angeles California 90095 United States School of Chemistry Chemical Engineering and Biotechnology Nanyang Technological University Singapore 637457 Singapore Nanobionics Group Department of Chemical and Biological Engineering Monash University Clayton Australia 3800 Monash

Humans rely increasingly on sensors to address grand challenges and to improve quality of life in the era of digitalization and big data. For ubiquitous sensing, flexible sensors are developed to overcome the limitations of conventional rigid counterparts. Despite rapid advancement in bench-side research over the last decade, the market adoption of flexible sensors remains limited. To ease and to expedite their deployment, here, we identify bottlenecks hindering the maturation of flexible sensors and propose promising solutions. We first analyze continued...challenges in achieving satisfactory sensing performance for real-world applications and then summarize issues in compatible sensor-biology interfaces, followed by brief discussions on powering and connecting sensor networks. Issues en route to commercialization and for sustainable growth of the sector are also analyzed, highlighting environmental concerns and emphasizing nontechnical issues such as business, regulatory, and ethical considerations. Additionally, we look at future intelligent flexible sensors. In proposing a comprehensive roadmap, we hope to steer research efforts towards common goals and to guide coordinated development strategies from disparate communities. Through such collaborative

关键词： soft materials mechanics engineering flexible electronics conformable sensors bioelectronics human-machine interfaces body area sensor networks technology translation sustainable electronics

来源：评论

学校读者我要写书评

暂无评论

Adaptive RBF-Neural-Network Control with Force Observer for Teleoperation Robotic System 1st

Adaptive RBF-Neural-Network Control with Force Observer for...

引用

1st International Conference on Cognitive Computation and systems, ICCCS 2022

作者： An, Zhaohui Min, Gaochen Jiang, Xiangzuo Yu, Xinbo He, Wei Silvestre, Carlos School of Intelligence Science and Technology Institute of Artificial Intelligence University of Science and Technology Beijing Beijing100083 China Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing Beijing100083 China Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education University of Science and Technology Beijing Beijing100083 China Donald Bren School of Information and Computer Sciences University of California IrvineCA92697 United States Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China LARSyS Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal

ISBN: (纸本)9789819927883

In this paper, an adaptive radial basis function neural network (RBFNN) control strategy is proposed for bilateral teleoperation robotic system with uncertainty and time delay. Meantime, the force observer method is used to estimate the interaction force between the slave robot and environment. The model of teleoperation robotic system is analyzed, and then the uncertainty of bilateral teleoperation robotic system is estimated by using RBFNN. Using Lyapunov stability theorem, the stability of teleoperation robotic system under our proposed control is proved. Finally, the effectiveness of the proposed control algorithm is verified by Matlab Simulink, and position tracking and force estimation performance of the teleoperation robotic system are guaranteed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Time delay

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：