检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shen, Chuyun Li, Wenhao Chen, Haoqing Wang, Xiaoling Zhu, Fengping Li, Yuxin Wang, Xiangfeng Jin, Bo School of Computer Science and Technology East China Normal University Shanghai200062 China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China Huashan Hospital Fudan University Shanghai200040 China School of Computer Science and Technology East China Normal University Shanghai AI Laboratory Shanghai200062 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China

Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the development of multimodal learning in medical image segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect. To emphasize, message-passing-based redundancy filtering allows neural network visualization techniques to visualize the knowledge relationship among different modalitie

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

A Uniform Representation Learning Method for OCT-based Fingerprint Presentation Attack Detection and Reconstruction

arXiv

引用

arXiv 2022年

作者： Zhang, Wentian Liu, Haozhe Liu, Feng Ramachandra, Raghavendra The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Gjøvik2818 Norway

The technology of optical coherence tomography (OCT) to fingerprint imaging opens up a new research potential for fingerprint recognition owing to its ability to capture depth information of the skin layers. Developing robust and high security Automated Fingerprint Recognition Systems (AFRSs) are possible if the depth information can be fully utilized. However, in existing studies, Presentation Attack Detection (PAD) and subsurface fingerprint reconstruction based on depth information are treated as two independent branches, resulting in high computation and complexity of AFRS ***, this paper proposes a uniform representation model for OCT-based fingerprint PAD and subsurface fingerprint reconstruction. Firstly, we design a novel semantic segmentation network which only trained by real finger slices of OCT-based fingerprints to extract multiple subsurface structures from those slices (also known as B-scans). The latent codes derived from the network are directly used to effectively detect the PA since they contain abundant subsurface biological information, which is independent with PA materials and has strong robustness for unknown PAs. Meanwhile, the segmented subsurface structures are adopted to reconstruct multiple subsurface 2D fingerprints. Recognition can be easily achieved by using existing mature technologies based on traditional 2D fingerprints. Extensive experiments are carried on our own established database, which is the largest public OCT-based fingerprint database with 2449 volumes. In PAD task, our method can improve 0.33% Acc from the state-of-the-art method. For reconstruction performance, our method achieves the best performance with 0.834 mean Intersection of Union (mIOU) and 0.937 Pixel Accuracy (PA). By comparing with the recognition performance on surface 2D fingerprints (e.g. commercial and high resolution), the effectiveness of our proposed method on high quality subsurface fingerprint reconstruction is further proved. Copyright ©

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

A survey: Deep learning for hyperspectral image classification with few labeled samples

arXiv

引用

arXiv 2021年

作者： Jia, Sen Jiang, Shuguo Lin, Zhijie Li, Nanying Xu, Meng Yu, Shiqi College of Computer Science and Software Engineering Shenzhen University China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China Department of Computer Science and Engineering Southern University of Science and Technology China

With the rapid development of deep learning technology and improvement in computing capability, deep learning has been widely used in the field of hyperspectral image (HSI) classification. In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance. However, in regard to HSI classification, a large number of labeled samples is generally difficult to acquire due to the difficulty and time-consuming nature of manual labeling. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. In this article, we concentrate on this topic and provide a systematic review of the relevant literature. Specifically, the contributions of this paper are twofold. First, the research progress of related methods is categorized according to the learning paradigm, including transfer learning, active learning and few-shot learning. Second, a number of experiments with various state-of-the-art approaches has been carried out, and the results are summarized to reveal the potential research directions. More importantly, it is notable that although there is a vast gap between deep learning models (that usually need sufficient labeled samples) and the HSI scenario with few labeled samples, the issues of small-sample sets can be well characterized by fusion of deep learning methods and related techniques, such as transfer learning and a lightweight model. For reproducibility, the source codes of the methods assessed in the paper can be found at https://***/ShuGuoJ/***. © 2021, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multilayer Fuzzy Neural Networks for Image Clustering

SSRN

引用

SSRN 2022年

作者： Wang, Yifan Ishibuchi, Hisao Er, Meng Joo Zhu, Jihua School of Software Engineering Xi’an Jiaotong University Xi’an710049 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation China College of Marine Electrical Engineering Dalian Maritime University Dalian116026 China Institute of Artificial Intelligence Marine Robotics China

Nowadays, labeling a huge number of images is still a very challenging task. To tackle the problem of unlabeled data, unsupervised learning has been proposed. Among many unsupervised learning algorithms, K-means is the most popular algorithm. However, in a low-dimensional space, fuzzy c-means, which is more robust and less sensitive to initialization, has several advantages over K-means clustering. On the other hand, stacked convolutional pooling structures and manifold representation play pivotal roles in image clustering. In this paper, we proposed an unsupervised multilayer fuzzy neural network for image clustering, which unifies fuzzy systems, multilayer convolutional structures and manifold representation. The main contributions of this work are: First, we extend fuzzy systems to unsupervised tasks by introducing the manifold representation. Next, we proposed the idea of using only a small number of attributes with the largest variances to compute firing strengths. This is to prevent the firing strengths from falling to zero in clustering high-dimensional data. Then, randomly generated convolutional weights are used to extract features, which is a good choice for data without labels. It is demonstrated on a wide range of image datasets that the proposed approach is superior to existing fuzzy and non-fuzzy clustering algorithms. © 2022, The Authors. All rights reserved.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Li, Wenhao Qiao, Dan Wang, Baoxiang Wang, Xiangfeng Jin, Bo Zha, Hongyuan School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen518172 China School of Computer Science and Technology East China Normal University Shanghai200062 China School of Software Engineering Tongji University Shanghai200062 China

The difficulty of appropriately assigning credit is particularly heightened in cooperative MARL with sparse reward, due to the concurrent time and structural scales involved. Automatic subgoal generation (ASG) has recently emerged as a viable MARL approach inspired by utilizing sub-goals in intrinsically motivated reinforcement learning. However, end-to-end learning of complex task planning from sparse rewards without prior knowledge, undoubtedly requires massive training samples. Moreover, the diversity-promoting nature of existing ASG methods can lead to the "over-representation" of sub-goals, generating numerous spurious sub-goals of limited relevance to the actual task reward and thus decreasing the sample efficiency of the algorithm. To address this problem and inspired by the disentangled representation learning, we propose a novel "disentangled" decision-making method, Semantically Aligned task decomposition in MARL (SAMA), that prompts pretrained language models with chain-of-thought that can suggest potential goals, provide suitable goal decomposition and subgoal allocation as well as self-reflection-based replanning. Additionally, SAMA incorporates language-grounded RL to train each agent's subgoal-conditioned policy. SAMA demonstrates considerable advantages in sample efficiency compared to state-of-the-art ASG methods, as evidenced by its performance on two challenging sparse-reward tasks, Overcooked and MiniRTS. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Robust Self-Expression Learning with Adaptive Noise Perception

SSRN

引用

SSRN 2023年

作者： Wang, Yangbo Zhou, Jie Lu, Jianglin Wan, Jun Gao, Can Lin, Qingshui College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China SMILE Lab Department of ECE College of Engineering Northeastern University Boston02115 United States School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China Basic Teaching Department Liaoning Technical University Huludao125105 China

Self-expression learning methods often obtain a coefficient matrix to measure the similarity between pairs of samples. However, directly using the raw data to represent each sample under the self-expression framework may not be ideal, as noise points are inevitably involved in the process of representing clean samples. To address this issue, this work proposes a novel self-expression model called robust Self-Expression learning with adaptive Noise Perception (SENP). SENP decomposes each sample into a clean part and a noisy part, and samples with large self-expression losses can be recognized as the noise points. A reliable coefficient matrix can then be learned by using only the clean points to reconstruct the clean part of each sample. By simultaneously detecting the noisy part of each sample and noise points, and adaptively mitigating their negative impacts, the representative ability of the generated coefficient matrix is improved. Moreover, inspired by the solution of non-negative matrix factorization (NMF), an effective algorithm is formed to optimize SENP. Extensive experiments on well-known benchmark datasets demonstrate the superiority of SENP compared to several state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning

arXiv

引用

arXiv 2022年

作者： Lu, Jianglin Zhou, Jie Chen, Yudong Pedrycz, Witold Hung, Kwok-Wai The College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States The College of Computer Science and Software Engineering Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The School of Information Technology and Electrical Engineering University of Queensland BrisbaneQLD4072 Australia The Department of Electrical & Computer Engineering University of Alberta Edmonton Canada The Systems Research Institute Polish Academy of Sciences Warsaw Poland Tencent Music Entertainment Guangdong Shenzhen518060 China

Thanks to the efficient retrieval speed and low storage consumption, learning to hash has been widely used in visual retrieval tasks. However, the known hashing methods assume that the query and retrieval samples lie in homogeneous feature space within the same domain. As a result, they cannot be directly applied to heterogeneous cross-domain retrieval. In this paper, we propose a Generalized Image Transfer Retrieval (GITR) problem, which encounters two crucial bottlenecks: 1) the query and retrieval samples may come from different domains, leading to an inevitable domain distribution gap;2) the features of the two domains may be heterogeneous or misaligned, bringing up an additional feature gap. To address the GITR problem, we propose an Asymmetric Transfer Hashing (ATH) framework with its unsupervised/semi-supervised/supervised realizations. Specifically, ATH characterizes the domain distribution gap by the discrepancy between two asymmetric hash functions, and minimizes the feature gap with the help of a novel adaptive bipartite graph constructed on cross-domain data. By jointly optimizing asymmetric hash functions and the bipartite graph, not only can knowledge transfer be achieved but information loss caused by feature alignment can also be avoided. Meanwhile, to alleviate negative transfer, the intrinsic geometrical structure of single-domain data is preserved by involving a domain affinity graph. Extensive experiments on both single-domain and cross-domain benchmarks under different GITR subtasks indicate the superiority of our ATH method in comparison with the state-of-the-art hashing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Multi-Branch Mutual-Distillation Transformer for EEG-Based Seizure Subtype Classification

arXiv

引用

arXiv 2024年

作者： Peng, Ruimin Du, Zhenbang Zhao, Changming Luo, Jingwei Liu, Wenzhong Chen, Xinxing Wu, Dongrui Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan430074 China AI Platform Software Engineering Research Center Dongfeng Corporation Research & Development Institute Wuhan430072 China China Electronic System Technology Co. Ltd. Beijing100089 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen518055 China

Cross-subject electroencephalogram (EEG) based seizure subtype classification is very important in precise epilepsy diagnostics. Deep learning is a promising solution, due to its ability to automatically extract latent patterns. However, it usually requires a large amount of training data, which may not always be available in clinical practice. This paper proposes Multi-Branch Mutual-Distillation (MBMD) Transformer for cross-subject EEG-based seizure subtype classification, which can be effectively trained from small labeled data. MBMD Transformer replaces all even-numbered encoder blocks of the vanilla Vision Transformer by our designed multi-branch encoder blocks. A mutual-distillation strategy is proposed to transfer knowledge between the raw EEG data and its wavelets of different frequency bands. Experiments on two public EEG datasets demonstrated that our proposed MBMD Transformer outperformed several traditional machine learning and state-of-the-art deep learning approaches. To our knowledge, this is the first work on knowledge distillation for EEG-based seizure subtype classification. © 2024, CC BY.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Sample hardness based gradient loss for long-tailed cervical cell detection

arXiv

引用

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation

arXiv

引用

arXiv 2024年

作者： Feng, Yifan Huang, Jiangang Du, Shaoyi Ying, Shihui Yong, Jun-Hai Li, Yipeng Ding, Guiguang Ji, Rongrong Gao, Yue School of Software BNRist THUIBCS BLBCI Tsinghua University Beijing100084 China Institute of Artificial Intelligence and Robotics College of Artificial Intelligence Xi’an Jiaotong University Xi’an710049 China The Department of Mathematics School of Science Shanghai University Shanghai200444 China The Department of Automation Tsinghua University Beijing100084 China The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Institute of Artificial Intelligence Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application Xiamen University 361005 China

We introduce Hyper-YOLO, a new object detection method that integrates hypergraph computations to capture the complex high-order correlations among visual features. Traditional YOLO models, while powerful, have limitations in their neck designs that restrict the integration of cross-level features and the exploitation of high-order feature interrelationships. To address these challenges, we propose the Hypergraph Computation Empowered Semantic Collecting and Scattering (HGC-SCS) framework, which transposes visual feature maps into a semantic space and constructs a hypergraph for high-order message propagation. This enables the model to acquire both semantic and structural information, advancing beyond conventional feature-focused learning. Hyper-YOLO incorporates the proposed Mixed Aggregation Network (MANet) in its backbone for enhanced feature extraction and introduces the Hypergraph-Based Cross-Level and Cross-Position Representation Network (HyperC2Net) in its neck. HyperC2Net operates across five scales and breaks free from traditional grid structures, allowing for sophisticated high-order interactions across levels and positions. This synergy of components positions Hyper-YOLO as a state-of-the-art architecture in various scale models, as evidenced by its superior performance on the COCO dataset. Specifically, HyperYOLO-N significantly outperforms the advanced YOLOv8-N and YOLOv9-T with 12% APval and 9% APval improvements. The source codes are at https://***/iMoonLab/Hyper-YOLO. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

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：