检索结果-内蒙古大学图书馆

Semi-heterogeneous three-way joint embedding network for sketch-based image retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lei, Jianjun Song, Yuxin Peng, Bo Ma, Zhanyu Shao, Ling Song, Yi-Zhe School of Electrical and Information Engineering Tianjin University Tianjin300072 China Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing100876 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates SketchX Lab Centre for Vision Speech and Signal Processing University of Surrey Surrey GuildfordGU2 7XH United Kingdom

Sketch-based image retrieval (SBIR) is a challenging task due to the large cross-domain gap between sketches and natural images. How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR. In this paper, we propose a novel semi-heterogeneous three-way joint embedding network (Semi3-Net), which integrates three branches (a sketch branch, a natural image branch, and an edgemap branch) to learn more discriminative cross-domain feature representations for the SBIR task. The key insight lies with how we cultivate the mutual and subtle relationships amongst the sketches, natural images, and edgemaps. A semi-heterogeneous feature mapping is designed to extract bottom features from each domain, where the sketch and edgemap branches are shared while the natural image branch is heterogeneous to the other branches. In addition, a joint semantic embedding is introduced to embed the features from different domains into a common high-level semantic space, where all of the three branches are shared. To further capture informative features common to both natural images and the corresponding edgemaps, a co-attention model is introduced to conduct common channel-wise feature recalibration between different domains. A hybrid-loss mechanism is designed to align the three branches, where an alignment loss and a sketch-edgemap contrastive loss are presented to encourage the network to learn invariant cross-domain representations. Experimental results on two widely used category-level datasets (Sketchy and TU-Berlin Extension) demonstrate that the proposed method outperforms state-of-the-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Meng, Lubin Huang, Jian Zeng, Zhigang Jiang, Xue Yu, Shan Jung, Tzyy-Ping Lin, Chin-Teng Chavarriaga, Ricardo Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Brainnetome Center National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China La Jolla CA United States Center for Advanced Neurological Engineering Institute of Engineering in Medicine Ucsd La Jolla CA United States Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Australia Zhaw DataLab Zürich University of Applied Sciences Winterthur8401 Switzerland

Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is implementable in practice and has never been considered before. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs and calling for urgent attention to address it. Copyright © 2020, The Authors. All rights reserved.

关键词： Electroencephalography

EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Meng, Lubin Huang, Jian Zeng, Zhigang Jiang, Xue Yu, Shan Jung, Tzyy-Ping Lin, Chin-Teng Chavarriaga, Ricardo Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Brainnetome Center and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China La Jolla CA United States Center for Advanced Neurological Engineering Institute of Engineering in Medicine UCSD La Jolla CA United States Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Australia ZHAW DataLab Zürich University of Applied Sciences Winterthur8401 Switzerland

Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to the wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks, e.g., the attacker can add tiny adversarial perturbations to a test sample to fool the model, or poison the training data to insert a secret backdoor. Previous research has shown that adversarial attacks are also possible for EEG-based BCIs. However, only adversarial perturbations have been considered, and the approaches are theoretically sound but very difficult to implement in practice. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is more feasible in practice and has never been considered before. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs. © 2021, CC BY.

关键词： Electroencephalography

A Multi-task Multi-stage Transitional Training Framework for Neural Chat Translation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Chulun Liang, Yunlong Meng, Fandong Zhou, Jie Xu, Jinan Wang, Hongji Zhang, Min Su, Jinsong School of Informatics Xiamen University Xiamen361005 China Beijing Jiaotong University Beijing100044 China Pattern Recognition Center WeChat AI Tencent Inc China Soochow University Suzhou215031 China School of Informatics Institute of Artificial Intelligence Xiamen University Xiamen361005 China Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage Fujian Taiwan Xiamen University Ministry of Culture and Tourism China Pengcheng Laboratory China

Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited resources of annotated bilingual dialogues;2) the neglect of modelling conversational properties;3) training discrepancy between different stages. To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues. We elaborately design two auxiliary tasks, namely utterance discrimination and speaker discrimination, to introduce the modelling of dialogue coherence and speaker characteristic into the NCT model. The training process consists of three stages: 1) sentence-level pre-training on large-scale parallel corpus;2) intermediate training with auxiliary tasks using additional monolingual dialogues;3) context-aware fine-tuning with gradual transition. Particularly, the second stage serves as an intermediate phase that alleviates the training discrepancy between the pre-training and fine-tuning stages. Moreover, to make the stage transition smoother, we train the NCT model using a gradual transition strategy, i.e., gradually transiting from using monolingual to bilingual dialogues. Extensive experiments on two language pairs demonstrate the effectiveness and superiority of our proposed training framework. © 2023, CC BY-NC-SA.

关键词：

Scene matching based on non-linear pre-processing on reference image and sensed image

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2005年第2期000卷

作者： ZHONG Sheng Zhang Tianxu Sang Nong State Key Lab for Image Processing & Intelligent Control， Institute for Pattern Recognition and Artificial Intelligence，Huazhong University of Science and Technology， Wuhan 430074， P. R. China

To solve the heterogeneous image scene matching problem, a non-linear pre-processing method for the original images before intensity-based correlation is proposed. The result shows that the proper matching probability... 详细信息

关键词： intensity-based correlation heterogeneous image scene matching

Entropy-based color image segmentation with alterable resolution

学校读者我要写书评

暂无评论

Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University 2005年第12期39卷 1975-1978页

作者： Ling, Jian-Guo Liu, Xiao-Jun Xu, Xin-He Yang, Jie Inst. of Image Processing and Pattern Recognition Shanghai Jiaotong Univ. Shanghai 200030 China Inst. of Artificial Intelligence and Robotics Northeastern Univ. Shenyang 110004 China The Second Inst. of Academy China Aerospace Science and Industry Corporation Beijing 100854 China

Two treatments of color image segmentation with information entropy were introduced: (1) The layers of the image are analyzed with whole information entropy and the segmentation resolution can be self-adapted;(2) The image is segmented with patch information entropy by segmenting the image in patch. According to the segmentation results, it can be found that the image segmentation with alterable resolution is more similar to the processing character of human vision.

关键词： image segmentation

Zero-Shot Audio Captioning Using Soft and Hard Prompts

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yiming Xu, Xuenan Du, Ruoyi Liu, Haohe Dong, Yuan Tan, Zheng-Hua Wang, Wenwu Ma, Zhanyu The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Electronic Systems Aalborg University Aalborg9220 Denmark The Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

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 sets 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, which, however, has received little attention. We propose an effective audio captioning method based on the contrastive language-audio pre-training (CLAP) model to address these issues. Our proposed method requires only textual data for training, enabling the model to generate text from the textual feature in the cross-modal semantic space. In the inference stage, the model generates the descriptive text for the given audio from the audio feature by leveraging the audio-text alignment from CLAP. We devise two strategies to mitigate the discrepancy between text and audio embeddings: a mixed-augmentation-based soft prompt and a retrieval-based acoustic-aware hard prompt. These approaches are designed to enhance the generalization performance of our proposed model, facilitating the model to generate captions more robustly and accurately. 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. © 2024, CC BY.

关键词： Semantics

Affine Non-negative Collaborative Representation Based pattern Classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yin, He-Feng Wu, Xiao-Jun Feng, Zhen-Hua Kittler, Josef School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

—During the past decade, representation-based classification methods have received considerable attention in pattern recognition. In particular, the recently proposed non-negative representation based classification (NRC) method has been reported to achieve promising results in a wide range of classification tasks. However, NRC has two major drawbacks. First, there is no regularization term in the formulation of NRC, which may result in unstable solution and misclassification. Second, NRC ignores the fact that data usually lies in a union of multiple affine subspaces, rather than linear subspaces in practical applications. To address the above issues, this paper presents an affine non-negative collaborative representation (ANCR) model for pattern classification. To be more specific, ANCR imposes a regularization term on the coding vector. Moreover, ANCR introduces an affine constraint to better represent the data from affine subspaces. The experimental results on several benchmarking datasets demonstrate the merits of the proposed ANCR method. The source code of our ANCR is publicly available at https://***/yinhefeng/ANCR. Copyright © 2020, The Authors. All rights reserved.

关键词： Vectors

Varifocal-Net: A Chromosome Classification Approach Using Deep Convolutional Networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Qin, Yulei Wen, Juan Zheng, Hao Huang, Xiaolin Yang, Jie Song, Ning Zhu, Yue-Min Wu, Lingqian Yang, Guang-Zhong Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Center for Medical Genetics School of Life Sciences Central South University Changsha410078 China Shanghai Key Laboratory of Reproductive Medicine School of Medicine Shanghai Jiao Tong University Shanghai200025 China Diagens-Hangzhou Hangzhou311121 China University Lyon INSA Lyon CNRS INSERM CREATIS UMR 5220 U1206F-69621 France Hamlyn Centre for Robotic Surgery Imperial College London SW72AZ United Kingdom

Chromosome classification is critical for karyotyping in abnormality diagnosis. To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosomes type and polarity using deep convolutional networks. The approach consists of one global-scale network (G-Net) and one local-scale network (L-Net). It follows three stages. The first stage is to learn both global and local features. We extract global features and detect finer local regions via the G-Net. By proposing a varifocal mechanism, we zoom into local parts and extract local features via the L-Net. Residual learning and multi-task learning strategies are utilized to promote high-level feature extraction. The detection of discriminative local parts is fulfilled by a localization subnet of the G-Net, whose training process involves both supervised and weakly-supervised learning. The second stage is to build two multi-layer perceptron classifiers that exploit features of both two scales to boost classification performance. The third stage is to introduce a dispatch strategy of assigning each chromosome to a type within each patient case, by utilizing the domain knowledge of karyotyping. Evaluation results from 1909 karyotyping cases showed that the proposed Varifocal-Net achieved the highest accuracy per patient case (%) of 99.2 for both type and polarity tasks. It outperformed state-of-the-art methods, demonstrating the effectiveness of our varifocal mechanism, multi-scale feature ensemble, and dispatch strategy. The proposed method has been applied to assist practical karyotype diagnosis. Copyright © 2018, The Authors. All rights reserved.

关键词： Computer aided diagnosis