检索结果-内蒙古大学图书馆

Polynomial stacked-attention network for nationality classification

Frontiers of Computer Science 2022年第4期16卷 215-217页

作者： Kunyan Li Jie Zhang Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing100190China University of Chinese Academy of Sciences Beijing100049China

1Introduction In recent years,nationality and region inference has atracted more and_more *** anthropological researches indicate that human faces are influenced by genes,and other external factors,e.g-,geographical environment[1].This relevance provides possible solutions for geographical area inference by ***,it remains a challenging task due to the tiny differences on faces for various countries,which is even hard for human beings to tell.

关键词： Polynomial s. network

来源：评论

学校读者我要写书评

暂无评论

Adversarial Example Defense via Perturbation Grading Strategy 9th

Adversarial Example Defense via Perturbation Grading Strate...

引用

9th International Forum on Digital Multimedia Communication, IFTC 2022

作者： Zhu, Shaowei Lyu, Wanli Li, Bin Yin, Zhaoxia Luo, Bin Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei China Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China School of Communication and Electronic Engineering East China Normal University Shanghai China

ISBN: (纸本)9789819908554

Deep Neural Networks have been widely used in many fields. However, studies have shown that DNNs are easily attacked by adversarial examples, which have tiny perturbations and greatly mislead the correct judgment of DNNs. Furthermore, even if malicious attackers cannot obtain all the underlying model parameters, they can use adversarial examples to attack various DNN-based task systems. Researchers have proposed various defense methods to protect DNNs, such as reducing the aggressiveness of adversarial examples by preprocessing or improving the robustness of the model by adding modules. However, some defense methods are only effective for small-scale examples or small perturbations but have limited defense effects for adversarial examples with large perturbations. This paper assigns different defense strategies to adversarial perturbations of different strengths by grading the perturbations on the input examples. Experimental results show that the proposed method effectively improves defense performance. In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Research on the Detection of Abnormal Cervical Cells Based on Improved YOLOv7

Research on the Detection of Abnormal Cervical Cells Based o...

引用

6th International Conference on intelligent Computing and Signal processing (ICSP)

作者： Xuewei Wang Shuang Yuan Lidong Yang Dawei Niu Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Inner Mongolia University of Science and Technology School of Digtial and Intelligence Industry Inner Mongolia China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Cervical cytologic screening is clinically important for the prevention and diagnosis of cervical cancer. Aiming at the many challenges in the detection of abnormal cervical cells, including the difficult detection of small targets of abnormal cervical cells, complex backgrounds, and uneven cell morphology, a detection algorithm for abnormal cervical cells based on improved YOLOv7 was proposed. The algorithm utilizes Deformable Convolutional Networks v2 (DCNv2) that adaptively de-tunes the scale and receptive field size to more effectively cope with the complexity and diversity of cervical cell images. The experimental results show that the improved YOLOv7 algorithm mAP achieves 57.26%, up to 73.88% accuracy, and 46.90% recall on the cervical abnormal cell dataset. Compared with the benchmark model, they increased by 4.07%, 3.39%, and 5.69%, respectively.

关键词： Accuracy Sensitivity Shape Prevention and mitigation Signal processing algorithms Signal processing Feature extraction Convolutional neural networks Detection algorithms Cervical cancer

来源：评论

学校读者我要写书评

暂无评论

Multiband Kick Drum Separation with Genre-Guided Optimization 10th

Multiband Kick Drum Separation with Genre-Guided Optimizati...

引用

10th Conference on Sound and Music Technology, CSMT 2023

作者： Li, Si Jiang, Yuanfeng Wang, Zhaowen Qian, Jiale Li, Wei School of Computer Science and Technology Fudan University Shanghai200438 China Department of Music AI and Information Technology Central Conservatory of Music Beijing100091 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789819779611

Kick drum plays an important role in electronic music. When hearing an excellent kick drum sound from a reference music track, music production beginners always feel confused about how it will sound if we solo the kick track and why it sounds perfect in a specific song. Reproducing the kick of a music track is not easy even for professional producers and arrangers. To investigate the ability of artificial intelligence in separating kick-drum sounds, in this paper we propose an end-to-end system which is capable of separating multi-genre high-quality electronic kick drum clips from mixed song tracks. Unlike most of the previous music source separation tasks, we only focus on the electronic kick drum rather than the whole percussion track. First, we design a multiband data representation approach for non-pitched percussions such as kick drums, then adopt a multi-discriminator module trained on a multi-genre kick drum corpus to further optimize the separated kick sound. To the authors’ knowledge, this study marks the first attempt at kick drum separation with stylistic optimization. Objective and subjective evaluations demonstrate that joint multiband representation and genre-guided optimisation can form a high-performance framework, showing a promising solution to the kick drum separation task. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Source separation

来源：评论

学校读者我要写书评

暂无评论

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity recognition 31

Beyond Boundaries: Learning a Universal Entity Taxonomy acro...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Yuming Zhao, Wantong Huang, Caishuang Ye, Junjie Wang, Xiao Zheng, Huiyuan Nan, Yang Wang, Yuran Xu, Xueying Huang, Kaixin Zhang, Yunke Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Honor Device Co. Ltd. Institute of Modern Languages and Linguistics Fudan University China Pengcheng Laboratory China Research Institute of Intelligent Complex Systems Fudan University China Shanghai Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9798891761964

Open Named Entity recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost their performance. However, training directly on existing datasets neglects their inconsistent entity definitions and redundant data, limiting LLMs to dataset-specific learning and hindering out-of-domain adaptation. To address this, we present B2NERD, a compact dataset designed to guide LLMs' generalization in Open NER under a universal entity taxonomy. B2NERD is refined from 54 existing English and Chinese datasets using a two-step process. First, we detect inconsistent entity definitions across datasets and clarify them by distinguishable label names to construct a universal taxonomy of 400+ entity types. Second, we address redundancy using a data pruning strategy that selects fewer samples with greater category and semantic diversity. Comprehensive evaluation shows that B2NERD significantly enhances LLMs' Open NER capabilities. Our B2NER models, trained on B2NERD, outperform GPT-4 by 6.8-12.0 F1 points and surpass previous methods in 3 out-of-domain benchmarks across 15 datasets and 6 languages. The data, models, and code are publicly available at https://***/UmeanNever/B2NER. © 2025 Association for Computational Linguistics.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Blur region detection and segmentation of partial blur image

Blur region detection and segmentation of partial blur image

引用

2021 International Conference on Signal processing and Communication Technology, SPCT 2021

作者： Wang, Kui-Kui Hou, Yi-Feng Lv, Mei-Ni Gong, Ping Yang, Qiu-Hui Gan, Hui Guangxi Key Laboratory of Image Processing and Intelligent Information System Wuzhou University Wuzhou543000 China

ISBN: (数字)9781510653344

ISBN: (纸本)9781510653337

In order to address the detection and segmentation of partial blur for natural images,a no-reference and training-free algorithm was proposed. Firstly, the test image was re-blurred by a Gaussian low-pass filter. Secondly, the pixel-wise singular value decomposition within N×N neighborhoods for both the test image and the re-blurred image were conducted to obtain the ratio of the end singular value to all singular value. According to the ratio,the blurriness distribution function was structured and the blurriness distribution map was drawed. Finally, combined with the K-means clustering algorithm and the erosion and dilation operations, the test image could be segmented into blur region and clear region. Experiment results show that the proposed approach can effectively detect and segment the partial blur image and behave well at precision, recall and F-score. © 2022 SPIE.

关键词： Distribution functions

来源：评论

学校读者我要写书评

暂无评论

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1178-1190页

作者： Hailong Ning Tao Lei Mengyuan An Hao Sun Zhanxuan Hu Asoke K.Nandi School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsShaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'anChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anChina School of Electronic Information and Artificial Intelligence Shaanxi University of Science and TechnologyXi'anChina School of Computer Central China Normal UniversityWuhanChina Department of Electronic and Electrical Engineering Brunel University LondonLondonUK Xi'an Jiaotong University Xi'anChina

Aerial scene recognition(ASR)has attracted great attention due to its increasingly essential *** of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ***,the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features,leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene *** addition,existing methods may suffer from poor generalisations due to millions of to‐belearnt parameters and inconsistent predictions between global and local *** tackle these problems,this study proposes a scale‐wise interaction fusion and knowledge distillation(SIF‐KD)network for learning robust and discriminative features with scaleinvariance and background‐independent *** main highlights of this study include two *** the one hand,a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene ***,a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local *** the other hand,a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during *** experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%,98.74%and 95.47%on the UCM,AID and NWPU‐RESISC45 datasets,respectively,compared with state of the arts.

关键词： deep learning image analysis image classification information fusion

来源：评论

学校读者我要写书评

暂无评论

Building Edge Detection Technology from Remote Sensing Image Based on NSCT and Tensor Voting 8

Building Edge Detection Technology from Remote Sensing Image...

引用

2024 8th International Conference on Machine Vision and information Technology, CMVIT 2024

作者： Wu, Yingbin Zhao, Peng Zhou, Mingquan Geng, Shengling Zhang, Dan School of Computer Science Qinghai Normal University Qinghai Xining China School of Mathematics and Information Technology Yuncheng University Shanxi Yuncheng China State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining China

An edge detection technology based on the combination of non-downsampling contour wave transform (NSCT) and tensor voting is proposed, which aims to obtain more accurate and detailed edge information of buildings in remote sensing images. Firstly, NSCT is used for image decomposition to obtain the subband frequency information of different scales and angles. Then, position encoding is performed on these subband coefficients to obtain second-order symmetric tensors at the corresponding positions. Tensors of different scales and angles at the same position are weighted and summed to complete feature fusion. Finally, the edge features of the image are obtained based on tensor voting theory. The experimental results show that compared to common edge detection technologies, such as Canny, Fast Edge (Fast edge detection using structured forests) and HED (Holistically-Nested Edge Detection), our method can more accurately and intensively reflect the boundaries of buildings and the edge information of roofs, providing better support for the analysis of building types and architectural styles. Compared to the HED method, which is based on deep learning, our method improves PSNR and SSIM metrics by 0.98 and 0.03, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Training Method to Ensemble Bi-Linear Models for Knowledge Graph Completion

An End-to-End Training Method to Ensemble Bi-Linear Models f...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Cen, Si Liu, Han Liu, Chao Zou, Xiaoying Dai, Guoquan Wang, Xizhao College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

ISBN: (纸本)9798350303780

The study of ensemble learning in knowledge graph embedding (KGE) shows that combining multiple individual KGE models can perform better on knowledge graph completion. However, existing KGE ensemble methods ignore the creation of model diversity because these methods independently train individual models, which are short of training interaction. To create rich model diversity, we propose a novel training method for ensemble bilinear models (EBM) for the problem of knowledge graph completion. EBM uses a weighted loss to allow individual KGE models to interact during training. In this way, the relations in the knowledge graph can be automatically modeled by the most appropriate model from the KGE individual ones. The experiments on knowledge graph completion show that EBM has richer diversity and performs better than the single bilinear model and the ensemble methods without interaction. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Improving viewpoint-independent object-centric representations through active viewpoint selection 24

Improving viewpoint-independent object-centric representatio...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Yinxuan Huang Chengmin Gao Bin Li Xiangyang Xue Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University

ISBN: (纸本)9798331314385

Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random or sequential viewpoint selection strategies. While applicable across various scenes, these strategies may not always be ideal, as certain scenes could benefit more from specific viewpoints. To address this limitation, we propose a novel active viewpoint selection strategy. This strategy predicts images from unknown viewpoints based on information from observation images for each scene. It then compares the object-centric representations extracted from both viewpoints and selects the unknown viewpoint with the largest disparity, indicating the greatest gain in information, as the next observation viewpoint. Through experiments on various datasets, we demonstrate the effectiveness of our active viewpoint selection strategy, significantly enhancing segmentation and reconstruction performance compared to random viewpoint selection. Moreover, our method can accurately predict images from unknown viewpoints.

关键词：

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：