检索结果-内蒙古大学图书馆

5th International Conference on Algorithms, Computing and artificial intelligence, ACAI 2022

作者： Pang, Yiwen Li, Ye Huang, Sheng-Jun College of Computer Science and Technology/Artificial Intelligence Nanjing University of Aeronautics and Astronautics China College of Computer Science and Technology/Artificial Intelligence Nanjing University of Aeronautics and Astronautics China and MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

ISBN: (纸本)9781450398343

Physics-informed neural networks (PINNs) have recently been demonstrated to be effective for the numerical solution of differential equations, with the advantage of small real labelled data needed. However, the performance of PINN greatly depends on the differential equation. The solution of singularly perturbed differential equations (SPDEs) usually contains a boundary layer, which makes it difficult for PINN to approximate the solution of SPDEs. In this paper, we analyse the reasons for the failure of PINN in solving SPDE and provide a feasible solution by adding prior knowledge of the boundary layer to the neural network. The new method is called the tailored physics-informed neural network (TPINN) since the network is tailored to some particular properties of the problem. Numerical experiments show that our method can effectively improve both the training speed and accuracy of neural networks. © 2022 ACM.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Copula-Nested Spectral Kernel Network 41

Copula-Nested Spectral Kernel Network

引用

41st International Conference on Machine Learning, ICML 2024

作者： Tian, Jinyue Xue, Hui Xue, Yanfang Fang, Pengfei School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

Spectral Kernel Networks (SKNs) emerge as a promising approach in machine learning, melding solid theoretical foundations of spectral kernels with the representation power of hierarchical architectures. At its core, the spectral density function plays a pivotal role by revealing essential patterns in data distributions, thereby offering deep insights into the underlying framework in real-world tasks. Nevertheless, prevailing designs of spectral density often overlook the intricate interactions within data structures. This phenomenon consequently neglects expanses of the hypothesis space, thus curtailing the performance of SKNs. This paper addresses the issues through a novel approach, the Copula-Nested Spectral Kernel Network (CokeNet). Concretely, we first redefine the spectral density with the form of copulas to enhance the diversity of spectral densities. Next, the specific expression of the copula module is designed to allow the excavation of complex dependence structures. Finally, the unified kernel network is proposed by integrating the corresponding spectral kernel and the copula module. Through rigorous theoretical analysis and experimental verification, CokeNet demonstrates superior performance and significant advancements over SOTA algorithms in the field. Copyright 2024 by the author(s)

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers 38

Cluster-Learngene: Inheriting Adaptive Clusters for Vision T...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Qiufeng Yang, Xu Feng, Fu Wang, Jing Geng, Xin School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

In recent years, the merging of vast datasets with powerful computational resources has led to the emergence of large pre-trained models in the field of deep learning. However, the common practices often overgeneralize the applicability of these models, overlooking the task-specific resource constraints. To mitigate this issue, we propose Cluster-Learngene, which effectively clusters critical internal modules from a large ancestry model and then inherits them to initialize descendant models of elastic scales. Specifically, based on the density characteristics of attention heads, our method adaptively clusters attention heads of each layer and position-wise feed-forward networks (FFNs) in the ancestry model as the learngene. Moreover, we introduce priority weight-sharing and learnable parameter transformations that expand the learngene to initialize descendant models of elastic scales. Through extensive experimentation, we demonstrate that Cluster-Learngene not only is more efficient compared to other initialization methods but also customizes models of elastic scales according to downstream task resources. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An image segmentation fusion algorithm based on density peak clustering and Markov random field

引用

Multimedia Tools and Applications 2024年第37期83卷 85331-85355页

作者： Feng, Yuncong Liu, Wanru Zhang, Xiaoli Zhu, Xiaoyan College of Computer Science and Engineering Changchun University of Technology Jilin Changchun130012 China Artificial Intelligence Research Institute Changchun University of Technology Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China College of Computer Science and Technology Jilin University Jilin Changchun130012 China

Image segmentation is a crucial task in the field of computer vision. Markov random fields (MRF) based image segmentation method can effectively capture intricate relationships among pixels. However, MRF typically requires an initial labeling field, and the number of classifications needs to be manually selected. To tackle these issues, we propose a novel medical image segmentation algorithm based on density peak clustering (DPC) and Markov random fields. Firstly, we improve DPC to make it applicable to grayscale images, named GIDPC. In the GIDPC method, local gray density and gray bias are defined to enable the automatic determination of the number of classifications. Then, GIDPC and MRF are combined to achieve image segmentation. Furthermore, a segmentation fusion method is employed to enhance the accuracy of image segmentation. We conduct comparison experiments on the whole brain atlas image library. Our proposed algorithm achieves high average values in uniformity measure, accuracy, precision and sensitivity, respectively. Experimental results demonstrate that the proposed algorithm outperforms other image segmentation methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Vision Transformers as Probabilistic Expansion from Learngene 41

Vision Transformers as Probabilistic Expansion from Learngen...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Qiufeng Yang, Xu Chen, Haokun Geng, Xin School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

Deep learning has advanced through the combination of large datasets and computational power, leading to the development of extensive pretrained models like Vision Transformers (ViTs). However, these models often assume a one-size-fits-all utility, lacking the ability to initialize models with elastic scales tailored to the resource constraints of specific downstream tasks. To address these issues, we propose Probabilistic Expansion from LearnGene (PEG) for mixture sampling and elastic initialization of Vision Transformers. Specifically, PEG utilizes a probabilistic mixture approach to sample Multi-Head Self-Attention layers and Feed-Forward Networks from a large ancestry model into a more compact part termed as learngene. Theoretically, we demonstrate that these learngene can approximate the parameter distribution of the original ancestry model, thereby preserving its significant knowledge. Next, PEG expands the sampled learngene through non-linear mapping, enabling the initialization of descendant models with elastic scales to suit various resource constraints. Our extensive experiments demonstrate the effectiveness of PEG and outperforming traditional initialization strategies. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

SEMI-Supervised Medical Image Segmentation via Dual Networks 22

SEMI-Supervised Medical Image Segmentation via Dual Networks

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Lu, Yunyao Wu, Yihang Kateb, Reem Chaddad, Ahmad College of Computer Science and Engineering Jeddah University Jeddah Saudi Arabia Aipm School of Artificial Intelligence Guilin University of Electronic Technology China École de Technologie Supérieure Laboratory for Imagery Vision and Artificial Intelligence Canada

ISBN: (纸本)9798331520526

Traditional supervised medical image segmentation models require large amounts of labeled data for training;however, obtaining such large-scale labeled datasets in the real world is extremely challenging. Recent semi-supervised segmentation models also suffer from noisy pseudo-label issue and limited supervision in feature space. To solve these challenges, we propose an innovative semi-supervised 3D medical image segmentation method to reduce the dependency on large, expert-labeled datasets. Furthermore, we introduce a dual-network architecture to address the limitations of existing methods in using contextual information and generating reliable pseudo-labels. In addition, a self-supervised contrastive learning strategy is used to enhance the representation of the network and reduce prediction uncertainty by distinguishing between reliable and unreliable predictions. Experiments on clinical magnetic resonance imaging demonstrate that our approach outperforms state-of-the-art techniques. Our code is available at https://***/AIPMLab/Semi-supervised-Segmentation. © 2025 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Semantic Segmentation with Selective Frequency Enhancement and Attention Mechanism for Tampering Detection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第6期5卷 3270-3283页

作者： Xu, Xu Lv, Wenrui Wang, Wei Zhang, Yushu Chen, Junxin Dalian University of Technology School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen518172 China Beijing Institute of Technology School of Medical Technology Beijing100081 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China

Nowadays, massive amounts of multimedia contents are exchanged in our daily life, while tampered images are also flooding the social networks. Tampering detection is therefore becoming increasingly important for multimedia integrity, and it is generally realized by designing specific convolutional neural networks. From a new perspective, this article proposes two pluggable modules for empowering existing semantic segmentation models for tampering detection. First, a selective frequency enhancement (SFE) module is developed to suppress the semantic information and selectively enhance the tamper information. Second, a boundary enhanced attention (BEA) module is designed to highlight the edge information of tempered area. Our SFE and BEA modules are combined with five mainstream semantic segmentation networks for performance evaluation. The experiment results demonstrate that our modules are able to empower the semantic segmentation networks for tampering detection, and their combinations even perform better than state-of-the-art algorithms in certain datasets. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models 38

Linearly Decomposing and Recomposing Vision Transformers for...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lin, Shuxia Zhang, Miaosen Chen, Ruiming Wang, Qiufeng Yang, Xu Geng, Xin School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

Vision Transformers (ViTs) are widely used in a variety of applications, while they usually have a fixed architecture that may not match the varying computational resources of different deployment environments. Thus, it is necessary to adapt ViT architectures to devices with diverse computational overheads to achieve an accuracy-efficient trade-off. This concept is consistent with the motivation behind Learngene. To achieve this, inspired by polynomial decomposition in calculus, where a function can be approximated by linearly combining several basic components, we propose to linearly decompose the ViT model into a set of components called learngenes during element-wise training. These learngenes can then be recomposed into differently scaled, pre-initialized models to satisfy different computational resource constraints. Such a decomposition-recomposition strategy provides an economical and flexible approach to generating different scales of ViT models for different deployment scenarios. Compared to model compression or training from scratch, which require to repeatedly train on large datasets for diverse-scale models, such strategy reduces computational costs since it only requires to train on large datasets once. Extensive experiments are used to validate the effectiveness of our method: ViTs can be decomposed and the decomposed learngenes can be recomposed into diverse-scale ViTs, which can achieve comparable or better performance compared to traditional model compression and pre-training methods. The code for our experiments is available in the supplemental material. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CRYSTAL DIFFUSION VARIATIONAL AUTOENCODER FOR PERIODIC MATERIAL GENERATION 10

CRYSTAL DIFFUSION VARIATIONAL AUTOENCODER FOR PERIODIC MATER...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Xie, Tian Fu, Xiang Ganea, Octavian-Eugen Barzilay, Regina Jaakkola, Tommi Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States

Generating the periodic structure of stable materials is a long-standing challenge for the material design community. This task is difficult because stable materials only exist in a low-dimensional subspace of all possible periodic arrangements of atoms: 1) the coordinates must lie in the local energy minimum defined by quantum mechanics, and 2) global stability also requires the structure to follow the complex, yet specific bonding preferences between different atom types. Existing methods fail to incorporate these factors and often lack proper invariances. We propose a Crystal Diffusion Variational Autoencoder (CDVAE) that captures the physical inductive bias of material stability. By learning from the data distribution of stable materials, the decoder generates materials in a diffusion process that moves atomic coordinates towards a lower energy state and updates atom types to satisfy bonding preferences between neighbors. Our model also explicitly encodes interactions across periodic boundaries and respects permutation, translation, rotation, and periodic invariances. We significantly outperform past methods in three tasks: 1) reconstructing the input structure, 2) generating valid, diverse, and realistic materials, and 3) generating materials that optimize a specific property. We also provide several standard datasets and evaluation metrics for the broader machine learning community. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Atoms

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：