检索结果-内蒙古大学图书馆

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

International Journal of Computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Agent-SiMT: Agent-Assisted Simultaneous Translation With Large Language Models

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 2074-2083页

作者： Shoutao Guo Shaolei Zhang Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) Beijing China University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of AI Safety Chinese Academy of Sciences Beijing China

Simultaneous Machine Translation (SiMT) generates target translations in real-time while reading the source sentence. It relies on a policy to determine the optimal timing for producing translations, aiming to achieve both low response latency and high translation quality. Existing SiMT methods typically utilize the traditional Transformer architecture, employing complicated dynamic programming algorithms to jointly optimize policy decisions and translation generation. While these methods excel at determining policies, their translation capabilities are suboptimal. In contrast, Large Language Models (LLMs), trained on extensive corpora, exhibit exceptional generation capabilities but struggle to learn translation policies through traditional Transformer-based training methods. To address these limitations, we introduce Agent-SiMT, a novel framework combining the strengths of LLMs and traditional SiMT methods. Agent-SiMT contains a policy-decision agent and a translation agent. The policy-decision agent is managed by a SiMT model, which determines the policy using partial source sentences and translations. The translation agent, powered by an LLM, generates the target translation according to the policy decisions. These two agents work collaboratively to perform SiMT. Experiments demonstrate that our method attains state-of-the-art performance.

关键词： Translation Hidden Markov models Transformers Training Large language models Collaboration Vocabulary Speech processing Memory modules Machine translation

来源：评论

学校读者我要写书评

暂无评论

SELF-SUPERVISED DIFFUSION MRI DENOISING VIA ITERATIVE AND STABLE REFINEMENT

arXiv

引用

arXiv 2025年

作者： Wu, Chenxu Kong, Qingpeng Jiang, Zihang Kevin Zhou, S. School of Biomedical Engineering Division of Life Sciences and Medicine USTC China MIRACLE Center Suzhou Institute for Advance Research USTC China State Key Laboratory of Precision and Intelligent Chemistry USTC China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology CAS China

Magnetic Resonance Imaging (MRI), including diffusion MRI (dMRI), serves as a "microscope" for anatomical structures and routinely mitigates the influence of low signal-to-noise ratio scans by compromising temporal or spatial resolution. However, these compromises fail to meet clinical demands for both efficiency and precision. Consequently, denoising is a vital preprocessing step, particularly for dMRI, where clean data is unavailable. In this paper, we introduce Di-Fusion, a fully self-supervised denoising method that leverages the latter diffusion steps and an adaptive sampling process. Unlike previous approaches, our single-stage framework achieves efficient and stable training without extra noise model training and offers adaptive and controllable results in the sampling process. Our thorough experiments on real and simulated data demonstrate that Di-Fusion achieves state-of-the-art performance in microstructure modeling, tractography tracking, and other downstream tasks. Code is available at https://***/FouierL/Di-Fusion. Copyright © 2025, The Authors. All rights reserved.

关键词： signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Lifetime Prediction of Topcon Modules Based on Accelerated Damp Heat Life Tests

SSRN

引用

SSRN 2025年

作者： Ren, Xingang Duan, Junwei Yang, Lixia Xu, Tao Yu, Yuanjie Chen, Zhiliang Lv, Ruirui Ye, Feihong Wang, Gang Ahmed, Rida Jiang, Hao Yang, Lixia Huang, Zhixiang Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui University Hefei230601 China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei230601 China CSI Cells Co. Ltd. Suzhou215129 China Anhui University of Chinese Medicine China Hong Kong Polytechnic University Hong Kong

Tunnel Oxide Passivation Contacts (TOPCon) solar cells have achieved high efficiency and become mainstream product in the global photovoltaic (PV) market. However, their long-term reliability, especially under high-temperature and high-humidity conditions, lacks sufficient field validation, and there is a lack of lifetime prediction models for TOPCon modules. To address this, we developed a robust accelerated aging model by integrating an improved Peck model with a sigmoidal degradation function, incorporating internal humidity and temperature as critical factors. The model employs a particle swarm optimization (PSO) algorithm to calibrate activation energy and humidity sensitivity parameters, enabling precise degradation trajectory simulation. Validated through a "fitting + testing" framework, the model achieves high accuracy (RMSE = 0.7%) in predicting power degradation under Damp Heat (DH), Highly Accelerated Stress Test (HAST), and modified Pressure Cooker Test (mPCT) conditions. Accelerated aging tests reveal that DH-induced degradation primarily reduces fill factor (FF) due to finger corrosion, with minimal impact on Voc and Isc. Experimental validation using a non-commercial corrosion-sensitive BOM combination shows that polyolefin elastomer (POE)-encapsulated modules exhibit superior corrosion resistance, projecting a service lifetime 23 years longer than EVA/EVA encapsulation in high-humidity regions like Hainan. This work bridges the gap in TOPCon module lifetime prediction under extreme environments, offering actionable insights for optimizing encapsulation materials and enhancing reliability. The model provides a scalable framework for evaluating module performance under site-specific climatic conditions, accelerating the development of durable PV technologies. © 2025, The Authors. All rights reserved.

关键词： Corrosion resistance

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

THREE-PRECISION ITERATIVE REFINEMENT WITH PARAMETER REGULARIZATION AND PREDICTION FOR SOLVING LARGE SPARSE LINEAR SYSTEMS

arXiv

引用

arXiv 2025年

作者： Ge, Jifeng Zhang, Juan Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan KeyLaboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

This study presents a novel mixed-precision iterative refinement algorithm, GADI-IR, within the general alternating-direction implicit (GADI) framework, designed for efficiently solving large-scale sparse linear systems. By employing low-precision arithmetic, particularly half-precision (FP16), for computationally intensive inner iterations, the method achieves substantial acceleration while maintaining high numerical accuracy. key challenges such as overflow in half-precision and convergence issues for low precision are addressed through careful backward error analysis and the application of a regularization parameter α. Furthermore, the integration of low-precision arithmetic into the parameter prediction process, using Gaussian Process Regression (GPR), significantly reduces computational time without degrading performance. The method is particularly effective for large-scale linear systems arising from discretized partial differential equations and other high-dimensional problems, where both accuracy and efficiency are critical. Numerical experiments demonstrate that the use of mixed-precision strategies not only accelerates computation but also ensures robust convergence, making the approach advantageous for various applications. The results highlight the potential of leveraging lower-precision arithmetic to achieve superior computational efficiency in high-performance computing. © 2025, CC BY.

关键词： Convergence of numerical methods

来源：评论

学校读者我要写书评

暂无评论

PaintingScapeVR: Exploring Gamified Interaction in Virtual Galleries 1st

PaintingScapeVR: Exploring Gamified Interaction in Virtual ...

引用

1st International Conference on Extended Reality, ICXR 2024

作者： Cai, Dongning Ren, Le Chang, Yaqi Li, Xiaodan Lin, Yuxin Yao, Junfeng Center for Digital Media Computing School of Film School of Informatics Xiamen University Xiamen361005 China Institute of Artificial Intelligence Xiamen University Xiamen361005 China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism New Taipei City Taiwan School of Informatics Xiamen University Xiamen361005 China

ISBN: (纸本)9789819636785

In reality, galleries usually display paintings in a protective manner, partly to delay the damage to the original artwork and ensure the long-term preservation of the artwork. On the other hand, it also hinders visitors’ deep appreciation and learning of the artwork. In the face of this challenge, our research aims to provide users with immersive viewing and entertainment, as well as interactive gaming experiences with artwork, through the use of virtual reality technology. So the paper proposes PaintingScapeVR, which is based on a virtual gallery and reproduces the three-dimensional scenes corresponding to different paintings. Visitors can freely explore in this virtual environment and gain a deeper understanding of the meaning and artistic value of artworks through interaction with them. Our results indicate that the reproduction of 3D scenes and gamified interactive design can not only significantly enhance visitors’ appreciation of painting art, but also leave a deeper learning impression. This immersive experience stimulates visitors’ desire to appreciate and explore, prompting them to actively delve into the background and techniques of art works, thereby enhancing their artistic appreciation abilities. At the same time, this work also demonstrates its potential in enhancing visitors’ understanding of painting works, allowing more people to explore the joy of painting and art. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Interactive gamification Three-dimensional displays Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Reliable Multi-Modal Object Re-Identification via Modality-Aware Graph Reasoning

arXiv

引用

arXiv 2025年

作者： Wan, Xixi Zheng, Aihua Wang, Zi Jiang, Bo Tang, Jin Ma, Jixin Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University Hefei230601 China School of Biomedical Engineering Anhui Medical University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China School of Computing and Mathematical Sciences University of Greenwich LondonSE10 9LS United Kingdom

Multi-modal data provides abundant and diverse object information, crucial for effective modal interactions in Re-Identification (ReID) tasks. However, existing approaches often overlook the quality variations in local features and fail to fully leverage the complementary information across modalities, particularly in the case of low-quality features. In this paper, we propose to address this issue by leveraging a novel graph reasoning model, termed the Modality-aware Graph Reasoning Network (MGRNet). Specifically, we first construct modality-aware graphs to enhance the extraction of fine-grained local details by effectively capturing and modeling the relationships between patches. Subsequently, the selective graph nodes swap operation is employed to alleviate the adverse effects of low-quality local features by considering both local and global information, enhancing the representation of discriminative information. Finally, the swapped modality-aware graphs are fed into the local-aware graph reasoning module, which propagates multimodal information to yield a reliable feature representation. Another advantage of the proposed graph reasoning approach is its ability to reconstruct missing modal information by exploiting inherent structural relationships, thereby minimizing disparities between different modalities. Experimental results on four benchmarks (RGBNT201, Market1501-MM, RGBNT100, MSVR310) indicate that the proposed method achieves state-of-the-art performance in multi-modal object ReID. The code for our method will be available upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

MEFA-Net: A mask enhanced feature aggregation network for polyp segmentation

引用

Computers in Biology and Medicine 2025年 186卷 109601-109601页

作者： Ke, Xiao Chen, Guanhong Liu, Hao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Accurate polyp segmentation is crucial for early diagnosis and treatment of colorectal cancer. This is a challenging task for three main reasons: (i) the problem of model overfitting and weak generalization due to the multi-center distribution of data;(ii) the problem of interclass ambiguity caused by motion blur and overexposure to endoscopic light;and (iii) the problem of intraclass inconsistency caused by the variety of morphologies and sizes of the same type of polyps. To address these challenges, we propose a new high-precision polyp segmentation framework, MEFA-Net, which consists of three modules, including the plug-and-play Mask Enhancement Module (MEG), Separable Path Attention Enhancement Module (SPAE), and Dynamic Global Attention Pool Module (DGAP). Specifically, firstly, the MEG module regionally masks the high-energy regions of the environment and polyps through a mask, which guides the model to rely on only a small amount of information to distinguish between polyps and background features, avoiding the model from overfitting the environmental information, and improving the robustness of the model. At the same time, this module can effectively counteract the "dark corner phenomenon" in the dataset and further improve the generalization performance of the model. Next, the SPAE module can effectively alleviate the inter-class fuzzy problem by strengthening the feature expression. Then, the DGAP module solves the intra-class inconsistency problem by extracting the invariance of scale, shape and position. Finally, we propose a new evaluation metric, MultiColoScore, for comprehensively evaluating the segmentation performance of the model on five datasets with different domains. We evaluated the new method quantitatively and qualitatively on five datasets using four metrics. Experimental results show that MEFA-Net significantly improves the accuracy of polyp segmentation and outperforms current state-of-the-art algorithms. Code posted on https://***/

关键词： Endoscopy

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：