检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Lv, Jinkai Hu, Yuyong Fu, Quanshui Zhang, Zhiwang Hu, Yuqiang Lv, Lin Yang, Guoqing Li, Jinpeng Zhao, Yi Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China The Research Center for Ubiquitous Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing China Suining Central Hospital Suining China Hwa Mei Hospital University of Chinese Academy of Sciences Ningbo China School of Electrical and Information Engineering The University of Sydney Sydney Australia School of Mathematics and Computer Sciences NanChang University Nanchang China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665468190

The convolutional-based methods provide good segmentation performance in the medical image segmentation task. However, those methods have the following challenges when dealing with the edges of the medical images: (1) Previous convolutional-based methods do not focus on the boundary relationship between foreground and background around the segmentation edge, which leads to the degradation of segmentation performance when the edge changes complexly. (2) The inductive bias of the convolutional layer cannot be adapted to complex edge changes and the aggregation of multiple-segmented areas, resulting in its performance improvement mostly limited to segmenting the body of segmented areas instead of the edge. To address these challenges, we propose the CM-MLP framework on MFI (Multiscale Feature Interaction) block and ACRE (axial context relation encoder) block for accurate segmentation of the edge of medical image. In the MFI block, we propose the cascade multi-scale MLP (Cascade MLP) to process all local information from the deeper layers of the network simultaneously and utilize a cascade multiscale mechanism to fuse discrete local information gradually. Then, the ACRE block is used to make the deep supervision focus on exploring the boundary relationship between foreground and background to modify the edge of the medical image. The segmentation accuracy (Dice) of our proposed CM-MLP framework reaches 96.96%, 96.76%, and 82.54% on three benchmark datasets: CVC-ClinicDB dataset, sub-Kvasir dataset, and our inhouse dataset, respectively, which significantly outperform the state-of-the-art method. The source code and trained models will be available at https://***/ProgrammerHyy/CM-MLP. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing

arXiv

引用

arXiv 2022年

作者： Nie, Lunyiu Sun, Jiuding Wang, Yanlin Du, Lun Hou, Lei Li, Juanzi Han, Shi Zhang, Dongmei Zhai, Jidong Department of Computer Science and Technology Tsinghua University China School of Software Engineering Sun Yat-Sen University China Microsoft Research Asia China

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task. Despite the promising performance, previous PLM-based approaches often suffer from hallucination problems due to their negligence of the structural information contained in the sentence, which essentially constitutes the key semantics of the logical forms. Furthermore, most works treat PLM as a black box in which the generation process of the target logical form is hidden beneath the decoder modules, which greatly hinders the model’s intrinsic interpretability. To address these two issues, we propose to incorporate the current PLMs with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks, namely Semantic Anchor Extraction and Semantic Anchor Alignment, for training the hierarchical decoders and probing the model intermediate representations in a self-adaptive manner alongside the fine-tuning process. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines. More importantly, by analyzing the intermediate representations of the hierarchical decoders, our approach also makes a huge step toward the intrinsic interpretability of PLMs in the domain of semantic parsing. © 2022, CC BY-SA.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Efficient reversible data hiding via two layers of double-peak embedding

arXiv

引用

arXiv 2022年

作者： Wu, Fuhu Sun, Jian Zhang, Shun Chen, Zhili School of Computer Science and Technology Anhui University Hefei230601 China Software Engineering Institute East China Normal University Shanghai200062 China

Reversible data hiding continues to attract significant attention in recent years. In particular, an increasing number of authors focus on the higher significant bit (HSB) plane of an image which can yield more redundant space. On the other hand, the lower significant bit plane is often discarded in existing schemes due to their harm to the embedding rate. This paper proposes an efficient reversible data hiding scheme via a double-peak two-layer embedding (DTLE) strategy with prediction error expansion. The higher six-bit planes of the image are assigned as the HSB plane, and double prediction error peaks are applied in either embedding layer. This makes fuller use of the redundancy space of images compared with the one error peak strategy. Moreover, we carry out the median-edge detector pre-processing for complex images to reduce the size of the auxiliary information. A series of experimental results show that our DTLE approach achieves up to 83% higher embedding rate on real-world data while providing better image quality. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation

arXiv

引用

arXiv 2023年

作者： Li, Qing Feng, Huifang Shi, Kanle Gao, Yue Fang, Yi Liu, Yu-Shen Han, Zhizhong School of Software Tsinghua University Beijing China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China School of Computer and Software Engineering Xihua University Chengdu China Kuaishou Technology Beijing China Center for Artificial Intelligence and Robotics New York University Abu Dhabi Abu Dhabi United Arab Emirates Department of Computer Science Wayne State University Detroit United States

We propose a novel method called SHS-Net for point cloud normal estimation by learning signed hyper surfaces, which can accurately predict normals with global consistent orientation from various point clouds. Almost all existing methods estimate oriented normals through a two-stage pipeline, i.e., unoriented normal estimation and normal orientation, and each step is implemented by a separate algorithm. However, previous methods are sensitive to parameter settings, resulting in poor results from point clouds with noise, density variations and complex geometries. In this work, we introduce signed hyper surfaces (SHS), which are parameterized by multi-layer perceptron (MLP) layers, to learn to estimate oriented normals from point clouds in an end-to-end manner. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. Specifically, we introduce a patch encoding module and a shape encoding module to encode a 3D point cloud into a local latent code and a global latent code, respectively. Then, an attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals. Experimental results show that our algorithm outperforms the state-of-the-art methods in both unoriented and oriented normal estimation. © 2023, CC BY-NC-SA.

关键词： Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

B-AUT: A Universal Architecture for Batch RFID Tags Authentication

B-AUT: A Universal Architecture for Batch RFID Tags Authenti...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yinan Zhu Chunhui Duan Xuan Ding Zheng Yang School of Software and BNRist Tsinghua University China School of Computer Science and Technology Beijing Institute of Technology China

ISBN: (纸本)9781665408790

RFID tags authentication is always a critical but challenging problem because only checking the EPC is vulnerable to counterfeiting attacks. Past works explore the unique backscat-ter signal features induced by tags' manufacturing imperfection as fingerprints, but fail to support simultaneous authentication for a batch of tags in practice, which is vital for large-scale RFID applications (e.g., warehouse inventory). In this paper, we present a universal architecture, namely B-AUT, to simultaneously authenticate multiple tags even with the same EPC and pinpoint them, which is fully compatible with Gen2 standard and applicable to almost all tags' hardware fingerprints proposed in existing works. The workflow of B-AUT is threefold based on our novel algorithms. First, the extracted fuzzy fingerprint and EPC are jointly exploited to cluster raw data. Second, we extract the tags' fine-grained fingerprints for genuineness validation and obtain the invalid clusters. Third, we harness localization methods to match the invalid cluster to dubious tags and further conduct small-scale re-validation to pinpoint the counterfeit tags. We have implemented a prototype of B-AUT and evaluated it in extreme cases. Experiment results demonstrate that B-AUT can maintain nearly the same authentication accuracy as that of separate authentication and reduce the time overhead by 43.3%. Moreover, the pinpointing accuracy can reach as high as 92.8%, regardless of tags' total quantities or tag models.

关键词： Location awareness Authentication Prototypes Fingerprint recognition Hardware Manufacturing Data mining

来源：评论

学校读者我要写书评

暂无评论

Toward a Unified Framework for Unsupervised Complex Tabular Reasoning

Toward a Unified Framework for Unsupervised Complex Tabular ...

引用

International Conference on Data Engineering

作者： Zhenyu Li Xiuxing Li Zhichao Duan Bowen Dong Ning Liu Jianyong Wang Department of Computer Science and Technology Tsinghua University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences School of Software Shandong University Jinan China

Structured tabular data exist across nearly all fields. Reasoning task over these data aims to answer questions or determine the truthiness of hypothesis sentences by understanding the semantic meaning of a table. While previous works have devoted significant efforts to the tabular reasoning task, they always assume there are sufficient labeled data. However, constructing reasoning samples over tables (and related text) is labor-intensive, especially when the reasoning process is complex. When labeled data is insufficient, the performance of models will suffer an unendurable decline. In this paper, we propose a unified framework for unsupervised complex tabular reasoning (UCTR), which generates sufficient and diverse synthetic data with complex logic for tabular reasoning tasks, assuming no human-annotated data at all. Specifically, we first utilize a random sampling strategy to collect diverse programs of different types and execute them on tables based on a "Program-Executor" module. To bridge the gap between the programs and natural language sentences, we design a powerful "NL-Generator" module to generate natural language sentences with complex logic from these programs. Since a table often occurs with its surrounding texts, we further propose novel "Table-to-Text" and "Text-to-Table" operators to handle joint table-text reasoning scenarios. This way, we can adequately exploit the unlabeled table resources to obtain a well-performed reasoning model under an unsupervised setting. Our experiments cover different tasks (question answering and fact verification) and different domains (general and specific), showing that our unsupervised methods can achieve at most 93% performance compared to supervised models. The impressive performance demonstrates that UCTR can significantly reduce the dependence on manual annotation. Moreover, we also find that it can substantially boost the supervised performance in low-resourced domains as a data augmentation technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ROBUST CROSS-SCENE FOREGROUND SEGMENTATION IN SURVEILLANCE VIDEO

ROBUST CROSS-SCENE FOREGROUND SEGMENTATION IN SURVEILLANCE V...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Liang, Dong Wei, Zongqi Sun, Han Zhou, Huiyu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Collaborative Innovation Center of Novel Software Technology and Industrialization China School of Informatics University of Leicester United Kingdom

ISBN: (纸本)9781665438643

Training only one deep model for large-scale cross-scene video foreground segmentation is challenging due to the off-the-shelf deep learning based segmentor relies on scene-specific structural information. This results in deep models that are scene-biased and evaluations that are scene-influenced. In this paper, we integrate dual modalities (foregrounds' motion and appearance), and then eliminating features without representativeness of foreground through attention-module-guided selective-connection structures. It is in an end-to-end training manner and to achieve scene adaptation in the plug and play style. Experiments indicate the proposed method significantly outperforms the state-of-the-art deep models and background subtraction methods in untrained scenes - LIMU and LASIESTA. Source Code is available at: https://***/WeiZongqi/HOFAM. © 2021 IEEE

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Based on Discriminative Generative Adversarial Network

引用

International Journal of Network Security 2021年第4期23卷 718-724页

作者： Appiah, Benjamin Qin, Zhiguang Nartey, Obed Tettey Agemang, Brighter Kanpogninge, Ansuura JohnBosco Aristotle School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China School of Computer Science and Software Engineering University of Electronic Science and Technology of China China

Generative adversarial network (GAN) has recently achieved remarkable success in anomaly detection. The GAN structure consists of a generator as an attacker and a discriminator as a classifier, all competing against each other. Most of the available classifiers are trained on softmax cross-entropy (SCE) loss function. However, the SCE loss is less discriminative in classifying malicious samples. To improve the discriminative power of these GAN’s classifiers, this paper proposes a discriminative GAN, D-GAN, for short. The key idea is to replace the SCE loss with Mahalanobis distance loss to induce strong intra-class compactness to construct high-density regions, which are essential to discriminating against new unseen classes. We evaluate D-GAN on MNIST and KDD99 datasets. The results demonstrate that D-GAN can achieve superior performance compared with several state-of-the-art SCE loss learning-based defending methods. © 2021

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

AFF-Dehazing: Attention-based feature fusion network for low-light image Dehazing

AFF-Dehazing: Attention-based feature fusion network for low...

引用

作者： Zhou, Yu Chen, Zhihua Sheng, Bin Li, Ping Kim, Jinman Wu, Enhua Department of Computer Science and Engineering East China University of Science and Technology Shanghai China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Department of Computing The Hong Kong Polytechnic University Kowloon Hong Kong School of Information Technologies The University of Sydney Sydney Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Faculty of Science and Technology University of Macau China

Images captured in haze conditions, especially at nighttime with low light, often suffer from degraded visibility, contrasts, and vividness, which makes it difficult to carry out the following vision tasks. In this article, we propose an attention-based feature fusion network (AFF-Dehazing) for low-light image dehazing. Our method decomposes the low-light image dehazing into two task-independent streams containing four modules: image dehazing module, low-light feature extractor module, feature fusion module, and image restoration module. The basic block of these modules is the proposed attention-based residual dense block. Since the dual-branch are used, AFF-Dehazing can avoid learning the mixed degradation all-in-one and enhance the details of low-light haze images. Extensive experiments show that our method surpasses previous state-of-the-art image dehazing methods and low-light enhancement methods by a very large margin both quantitatively and qualitatively. © 2021 John Wiley & Sons, Ltd.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Recognizing Private Handwritten Numbers

Federated Learning for Recognizing Private Handwritten Numbe...

引用

2021 IEEE International Conference on Data science and computer Application, ICDSCA 2021

作者： Wang, Di Jiang, Yuchen Zhao, Yibo Chen, Panyang Li, Ang Pan, Kun Institution of Information Engineering Chinese Academy of Sciences State Key Laboratory of Information Security Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Computer Science and Technology College of Computer Science Chongqing University Chongqing China Zibo Shiyan High School International Division Zibo Shandong China Computer Science Department of Computer Science and Software Engineering Auburn University Auburn United States Shanghai Shangde Experimental School Shanghai China School of Computing University of Leeds Leeds United Kingdom

ISBN: (纸本)9781665440530

Federated learning (FL) is a new technology in the field of machine learning, which trains an algorithm across multiple decentralized edge devices or servers holding data samples, without exchanging their data samples. Horizontal Federated Learning (HFL) is a FL method focusing on using the same feature space across all users, which is suitable for situations where users' data feature dimensions overlap more. Because FL has the advantage of privacy protection in the field of manufacturing, we propose an HFL-based deep learning method named FedCNN, which realizes the digits handwritten recognition without violating the privacy or data sharing. Three different methods (local model, centralized model, and HFL-based FedCNN) are used on a public data set (MINIST) to compare the pros and cons of the solutions. The experimental results demonstrate that FedCNN scheme can simultaneously achieve practical privacy preservation and good model generalization performance with Homomorphic Encryption. © 2021 IEEE.

关键词： Data privacy

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：