检索结果-内蒙古大学图书馆

Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Cheng, Zihan Guo, Jintao Zhang, Jian Qi, Lei Zhou, Luping Shi, Yinghuan Gao, Yang Shanghai Jiao Tong University School of Medicine Shanghai200025 China Nanjing University National Institute of Healthcare Data Science Jiangsu Nanjing210093 China Nanjing University State Key Laboratory for Novel Software Technology National Institute of Healthcare Data Science Jiangsu Nanjing210093 China Southeast University School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Jiangsu Nanjing211189 China The University of Sydney School of Electrical and Information Engineering SydneyNSW2006 Australia

To segment medical images with distribution shifts, domain generalization (DG) has emerged as a promising setting to train models on source domains that can generalize to unseen target domains. Existing DG methods are mainly based on CNN or ViT architectures. Recently, advanced state space models, represented by Mamba, have shown promising results in various supervised medical image segmentation. The success of Mamba is primarily owing to its ability to capture long-range dependencies while keeping linear complexity with input sequence length, making it a promising alternative to CNNs and ViTs. Inspired by the success, in the paper, we explore the potential of the Mamba architecture to address distribution shifts in DG for medical image segmentation. Specifically, we propose a novel Mamba-based framework, Mamba-Sea, incorporating global-to-local sequence augmentation to improve the model’s generalizability under domain shift issues. Our Mamba-Sea introduces a global augmentation mechanism designed to simulate potential variations in appearance across different sites, aiming to suppress the model’s learning of domain-specific information. At the local level, we propose a sequence-wise augmentation along input sequences, which perturbs the style of tokens within random continuous sub-sequences by modeling and resampling style statistics associated with domain shifts. To our best knowledge, Mamba-Sea is the first work to explore the generalization of Mamba for medical image segmentation, providing an advanced and promising Mamba-based architecture with strong robustness to domain shifts. Remarkably, our proposed method is the first to surpass a Dice coefficient of 90% on the Prostate dataset, which exceeds previous SOTA of 88.61%. © 1982-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Delving into Invisible Semantics for Generalized One-shot Neural Human Rendering

引用

IEEE Transactions on Visualization and Computer Graphics 2025年

作者： Lin, Yihong Xu, Xuemiao Zhang, Huaidong Xu, Cheng Li, Weijie Xie, Yi Qin, Jing He, Shengfeng South China University of Technology Guangdong China Guangdong Engineering Center for Large Model and GenAI Technology State Key Laboratory of Subtropical Building and Urban Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China South China University of Technology China Hong Kong Polytechnic University Centre for Smart Health Hong Kong CAS-Hong Kong Joint Laboratory for Multimodal Medical Molecular Imaging Hong Kong Singapore Management University School of Computing and Information Systems Singapore

Traditional human neural radiance fields often overlook crucial body semantics, resulting in ambiguous reconstructions, particularly in occluded regions. To address this problem, we propose the Super-Semantic Disentangled Neural Renderer (SSD-NeRF), which employs rich regional semantic priors to enhance human rendering accuracy. This approach initiates with a Visible-Invisible Semantic Propagation module, ensuring coherent semantic assignment to occluded parts based on visible body segments. Furthermore, a Region-Wise Texture Propagation module independently extends textures from visible to occluded areas within semantic regions, thereby avoiding irrelevant texture mixtures and preserving semantic consistency. Additionally, a view-aware curricular learning approach is integrated to bolster the model's robustness and output quality across different viewpoints. Extensive evaluations confirm that SSD-NeRF surpasses leading methods, particularly in generating quality and structurally semantic reconstructions of unseen or occluded views and poses. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Predicting links and their building lime: A path-based approach 30

Predicting links and their building lime: A path-based appro...

引用

30th AAAI Conference on Artificial Intelligence, AAAI 2016

作者： Li, Manling Jia, Yantao Wang, Yuanzhuo Zhao, Zeya Cheng, Xueqi Institute of Computing Technology Key lab of Network Data Science and Technology CAS Beijing100190 China

ISBN: (纸本)9781577357605

Predicting links and their building time in a knowledge network has been extensively studied in recent years. Most structure-based predictive methods consider structures and the time information of edges separately, which fail to characterize the correlation between them. In this paper, we propose a structure callcd the Time-Difference-labeled Path, and a link prediction method (TDLP). Experiments show that TDLP outperforms the state-of-the-art methods. Links and Building Time Prediction. © 2016, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

A Contrastive Pre-training Approach to Discriminative Autoencoder for Dense Retrieval 22

A Contrastive Pre-training Approach to Discriminative Autoen...

引用

31st ACM International Conference on Information and Knowledge Management, CIKM 2022

作者： Ma, Xinyu Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi Cas Key Lab of Network Data Science and Technology Ict Cas University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781450392365

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained autoencoder-based language models with a weak decoder can provide high-quality text representations, boosting the effectiveness and few-shot ability of DR models. However, even a weak autoregressive decoder has the bypass effect on the encoder. More importantly, the discriminative ability of learned representations may be limited since each token is treated equally important in decoding the input texts. To address the above problems, in this paper, we propose a contrastive pre-training approach to learn a discriminative autoencoder with a lightweight multi-layer perception (MLP) decoder. The basic idea is to generate word distributions of input text in a non-autoregressive fashion and pull the word distributions of two masked versions of one text close while pushing away from others. We theoretically show that our contrastive strategy can suppress the common words and highlight the representative words in decoding, leading to discriminative representations. Empirical results show that our method can significantly outperform the state-of-the-art autoencoder-based language models and other pre-trained models for dense retrieval. © 2022 ACM.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Sparse word embeddings using l1 regularized online learning 25

Sparse word embeddings using l1 regularized online learning

引用

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Sun, Fei Guo, Jiafeng Lan, Yanyan Xu, Jun Xueqi, Cheng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

Recently, Word2Vec tool has attracted a lot of interest for its promising performances in a variety of natural language processing (NLP) tasks. However, a critical issue is that the dense word representations learned in Word2Vec are lacking of interpretability. It is natural to ask if one could improve their interpretability while keeping their performances. Inspired by the success of sparse models in enhancing interpretability, we propose to introduce sparse constraint into Word2Vec. Specifically, we take the Continuous Bag of Words (CBOW) model as an example in our study and add the l regularizer into its learning objective. One challenge of optimization lies in that stochastic gradient descent (SGD) cannot directly produce sparse solutions with l regularizer in online training. To solve this problem, we employ the Regularized Dual Averaging (RDA) method, an online optimization algorithm for regularized stochastic learning. In this way, the learning process is very efficient and our model can scale up to very large corpus to derive sparse word representations. The proposed model is evaluated on both expressive power and interpretability. The results show that, compared with the original CBOW model, the proposed model can obtain state-of-the-art results with better interpretability using less than 10% non-zero elements.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

An ensemble method for job recommender systems 10

An ensemble method for job recommender systems

引用

10th ACM Conference on Recommender Systems Challenge, RecSys Challenge 2016

作者： Zhang, Chenrui Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781450348010

In this paper, we present an ensemble method for job recommendation to ACM RecSys Challenge 2016. Given a user, the goal of a job recommendation system is to predict those job postings that are likely to be relevant to the user1. Firstly, we analyze the train dataset and find several interesting patterns. Secondly, we describe our solution, which is an ensemble of two filters, combining the merits of traditional collaborative filtering and content-based filtering. Our approach finally achieved a score of 1632828.82, ranked at the 10th place on the public leaderboard. © 2016 ACM.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Dynamic-K recommendation with personalized decision boundary 23rd

Dynamic-K recommendation with personalized decision boundary

引用

23rd China conference on Information Retrieval, CCIR 2017

作者： Gao, Yan Guo, Jiafeng Lan, Yanyan Liao, Huaming CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783319686981

In this paper, we investigate the recommendation task in the most common scenario with implicit feedback (e.g., clicks, purchases). State-of-the-art methods in this direction usually cast the problem as to learn a personalized ranking on a set of items (e.g., webpages, products). The top-N results are then provided to users as recommendations, where the N is usually a fixed number pre-defined by the system according to some heuristic criteria (e.g., page size, screen size). There is one major assumption underlying this fixed-number recommendation scheme, i.e., there are always sufficient relevant items to users’ preferences. Unfortunately, this assumption may not always hold in real-world scenarios. In some applications, there might be very limited candidate items to recommend, and some users may have very high relevance requirement in recommendation. In this way, even the top-1 ranked item may not be relevant to a user’s preference. Therefore, we argue that it is critical to provide a dynamic-K recommendation, where the K should be different with respect to the candidate item set and the target user. We formulate this dynamic-K recommendation task as a joint learning problem with both ranking and classification objectives. The ranking objective is the same as existing methods, i.e., to create a ranking list of items according to users’ interests. The classification objective is unique in this work, which aims to learn a personalized decision boundary to differentiate the relevant items from irrelevant items. Based on these ideas, we extend two state-of-the-art ranking-based recommendation methods, i.e., BPRMF and HRM, to the corresponding dynamic-K versions, namely DK-BPRMF and DK-HRM. Our experimental results on two datasets show that the dynamic-K models are more effective than the original fixed-N recommendation methods. © Springer International Publishing AG 2017.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

FM-FCN:A Neural network with Filtering Modules for Accurate Vital Signs Extraction

引用

Research 2025年第1期2024卷 92-106页

作者： Fangfang Zhu Qichao Niu Xiang Li Qi Zhao Honghong Su Jianwei Shuai Department of Physics and Fujian Provincial Key Laboratory for Soft Functional Materials ResearchXiamen UniversityXiamen 361005China National Institute for Data Science in Health and Medicine and State Key Laboratory of Cellular Stress BiologyInnovation Center for Cell Signaling NetworkXiamen UniversityXiamen 361005China Vitalsilicon Technology Co.Ltd. JiaxingZhejiang 314006China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan 114051China Yangtze Delta Region Institute of Tsinghua University ZhejiangJiaxing 314006China Wenzhou Institute University of Chinese Academy of SciencesWenzhou 325001China Oujiang Laboratory (Zhejiang Lab for Regenerative Medicine Vision and Brain Health)Wenzhou 325001China

Neural networks excel at capturing local spatial patterns through convolutional modules,but they may struggle to identify and effectively utilize the morphological and amplitude periodic nature of physiological *** this work,we propose a novel network named filtering module fully convolutional network(FM-FCN),which fuses traditional filtering techniques with neural networks to amplify physiological signals and suppress ***,instead of using a fully connected layer,we use an FCN to preserve the time-dimensional correlation information of physiological signals,enabling multiple cycles of signals in the network and providing a basis for signal ***,we introduce the FM as a network module that adapts to eliminate unwanted interference,leveraging the structure of the *** approach builds a bridge between deep learning and signal processing ***,we evaluate the performance of FM-FCN using remote *** results demonstrate that FM-FCN outperforms the second-ranked method in terms of both blood volume pulse(BVP)signal and heart rate(HR)*** substantially improves the quality of BVP waveform reconstruction,with a decrease of 20.23%in mean absolute error(MAE)and an increase of 79.95%in signal-to-noise ratio(SNR).Regarding HR estimation accuracy,FM-FCN achieves a decrease of 35.85%in MAE,29.65%in error standard deviation,and 32.88%decrease in 95%limits of agreement width,meeting clinical standards for HR accuracy *** results highlight its potential in improving the accuracy and reliability of vital sign measurement through high-quality BVP signal *** codes and datasets are available online at https://***/zhaoqi106/FM-FCN.

关键词： physiological signalsin filtering module fully convolutional network fm fcn which vital signs extraction amplify physiological signals convolutional modulesbut neural networks filtering module capturing local spatial patterns

来源：评论

学校读者我要写书评

暂无评论

Multi-task representation learning for demographic prediction 38th

Multi-task representation learning for demographic predictio...

引用

38th European Conference on Information Retrieval Research, ECIR 2016

作者： Wang, Pengfei Guo, Jiafeng Lan, Yanyan Xu, Jun Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Beijing China

ISBN: (纸本)9783319306704

Demographic attributes are important resources for market analysis, which are widely used to characterize different types of users. However, such signals are only available for a small fraction of users due to the difficulty in manual collection process by retailers. Most previous work on this problem explores different types of features and usually predicts different attributes independently. However, manually defined features require professional knowledge and often suffer from under specification. Meanwhile, modeling the tasks separately may lose the ability to leverage the correlations among different attributes. In this paper, we propose a novel Multi-task Representation Learning (MTRL) model to predict users’ demographic attributes. Comparing with the previous methods, our model conveys the following merits: (1) By using a multitask approach to learn the tasks, our model leverages the large amounts of cross-task data, which is helpful to the task with limited data;(2) MTRL uses a supervised way to learn the shared semantic representation across multiple tasks, thus it can obtain a more general and robust representation by considering the constraints among tasks. Experiments are conducted on a real-world retail dataset where three attributes (gender, marital status, and education background) are predicted. The empirical results show that our MTRL model can improve the performance significantly compared with the state-of-the-art baselines. © Springer International Publishing Switzerland 2016.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework

Controlling Risk of Retrieval-augmented Generation: A Counte...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Chen, Lu Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761681

Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it is that a RAG model's prediction is incorrect, resulting in uncontrollable risks in real-world applications. In this work, we emphasize the importance of risk control, ensuring that RAG models proactively refuse to answer questions with low confidence. Our research identifies two critical latent factors affecting RAG's confidence in its predictions: the quality of the retrieved results and the manner in which these results are utilized. To guide RAG models in assessing their own confidence based on these two latent factors, we develop a counterfactual prompting framework that induces the models to alter these factors and analyzes the effect on their answers. We also introduce a benchmarking procedure to collect answers with the option to abstain, facilitating a series of experiments. For evaluation, we introduce several risk-related metrics and the experimental results demonstrate the effectiveness of our approach. Our code and benchmark dataset are available at https://***/ictbigdatalab/RC-RAG. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：