检索结果-内蒙古大学图书馆

27th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2021

作者： Wang, Zhaokang Li, Junhong Qi, Yifan Zhu, Guanghui Yuan, Chunfeng Huang, Yihua Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Nanjing University Department of Computer Science and Technology Nanjing China

ISBN: (纸本)9781665408783

The industry and academia have proposed many distributed graph processing systems. However, the existing systems are not friendly enough for users like data analysts and algorithm engineers. On the one hand, the programming models and interfaces differ a lot in the existing systems, leading to high learning costs and program migration costs. On the other hand, these graph processing systems are tightly bound to the underlying distributed computing platforms, requiring users to be familiar with distributed computing. To improve the usability of distributed graph processing, we propose a unified distributed graph programming framework UniGPS. Firstly, we propose a unified cross-platform graph programming model VCProg for UniGPS. VCProg hides details of distributed computing from users. It is compatible with the popular graph programming models Pregel, GAS, and Push-Pull. VCProg-based programs can be executed by compatible distributed graph processing systems without modification, reducing the learning overheads of users. Secondly, UniGPS supports Python as the programming language. We propose an interprocess-communication-based execution environment isolation mechanism to enable Java/C++-based graph processing systems to call user-defined methods written in Python. The experimental results show that UniGPS enables users to process big graphs beyond the memory capacity of a single machine without sacrificing usability. UniGPS shows near-linear data scalability and machine scalability. © 2021 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Accurate and Complete Captions for Question-controlled Text-aware Image Captioning

Accurate and Complete Captions for Question-controlled Text-...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yehuan Wang Jian Hu Lin Shang Department of Computer Science and Technology State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Mechanical Engineering Nanjing University of Science and Technology Nanjing China

Question-controlled Text-aware Image Captioning (Qc-TextCap), is the task of generating a distinctive scene text aware caption according to several personalized questions when given an image. However, due to the diversity of visual scene, it is hard for current Optical Character Recognition (OCR) systems to extract complete scene text sentences from the images. Besides, existing works are limited in their use of question features and visual features. In this paper, we propose a Multimodal Transformer plus Scene text clustering and Cross modal attention (MTSC) to tackle the above challenges. We devise scene text clustering to group relevant scene text pieces which are detected as separate results by current OCR systems. To better utilize the information in questions and images, we design cross modal attention to enrich the features of both modalities. We extensively evaluate our model on the two Qc-TextCap datasets and superior results are achieved when comparing to state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VALAR: Streamlining Alarm Ranking in Static Analysis with Value-Flow Assisted Active Learning

VALAR: Streamlining Alarm Ranking in Static Analysis with Va...

引用

IEEE International Conference on Automated software Engineering (ASE)

作者： Pengcheng Liu Yifei Lu Wenhua Yang Minxue Pan State Key Laboratory for Novel Software Technology Software Institute Nanjing University China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China

Static analyzers play a critical role in program defects and security vulnerabilities detection. Despite their importance, the widespread adoption of static analysis techniques in industrial development faces numerous obstacles, among which the high rate of false alarms constitutes a significant one. To address this issue, we propose a novel approach called Valar, which performs alarm ranking for advanced value-flow analysis using the active learning technique. Active learning algorithms minimize the manual effort for alarm inspection by maximizing the effect of each user labeling in recognizing true/false alarms. Meanwhile, the value-flows provide Valar with a concise and comprehensive summary of the operational semantics about programs. Based on this, Valar is able to reason about the potential correlations between alarms and prioritize the most profitable unlabeled alarm. Additionally, the accuracy of Valar increases as more user labels are given and Valar's active learning model is further refined. We evaluate Valar on 20 real-world C/C++ programs using three value-flow based checkers. Our experimental results demonstrated that Valar significantly lowers the priorities of false alarms with most true alarms ranked high. Notably, Valar ranked all true alarms in the top 47% in 90% projects and ranked 90% true alarms in the top 22% in 75% projects. Furthermore, Valar has no requirement for pretraining and has a negligible computation time of less than 0.1s for each alarm prioritization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal Policies for Quantum Markov Decision Processes

引用

International Journal of Automation and computing 2021年第3期18卷 410-421页

作者： Ming-Sheng Ying Yuan Feng Sheng-Gang Ying Centre for Quantum Software and Information University of Technology SydneyNSW 2007Australia State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

Markov decision process(MDP)offers a general framework for modelling sequential decision making where outcomes are *** particular,it serves as a mathematical framework for reinforcement *** paper introduces an extension of MDP,namely quantum MDP(q MDP),that can serve as a mathematical model of decision making about quantum *** develop dynamic programming algorithms for policy evaluation and finding optimal policies for q MDPs in the case of *** results obtained in this paper provide some useful mathematical tools for reinforcement learning techniques applied to the quantum world.

关键词： Quantum Markov decision processes quantum machine learning reinforcement learning dynamic programming decision making

来源：评论

学校读者我要写书评

暂无评论

A Channel Mix Method for Fine-Grained Cross-Modal Retrieval

A Channel Mix Method for Fine-Grained Cross-Modal Retrieval

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Shen, Yang Sun, Xuhao Wei, Xiu-Shen Hu, Hanxu Chen, Zhipeng School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Xidian University State Key Laboratory of Integrated Services Networks Xi'an China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China University of Edinburgh Edinburgh United Kingdom Beijing China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

In this paper, we propose a simple but effective method for dealing with the challenging fine-grained cross-modal retrieval task where it aims to enable flexible retrieval among subor-dinate categories across different modalities. Specifically, in order to enhance information interaction in different modalities for fine-grained objects, a channel mix method is developed and performed upon the channels of deep activations across dif-ferent modalities. After that, a 1 x 1 convolution is employed to aggregate the mixed channels into a unified feature vector. Moreover, equipped with a novel fine-grained cross-modal cen-ter loss, our method can further improve the intra-class separa-bility as well as inter-class compactness for multi-modalities. Experiments are conducted on the fine-grained cross-modal benchmark dataset and show our superiority over competing methods. Meanwhile, ablation studies also demonstrate the effectiveness of our proposals. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Adaptive Plasticity Improvement for Continual Learning

Adaptive Plasticity Improvement for Continual Learning

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yan-Shuo Liang Wu-Jun Li Department of Computer Science and Technology National Key Laboratory for Novel Software Technology Nanjing University P. R. China

Many works have tried to solve the catastrophic forgetting (CF) problem in continual learning (lifelong learning). However, pursuing non-forgetting on old tasks may damage the model's plasticity for new tasks. Although some methods have been proposed to achieve stability-plasticity trade-off, no methods have considered evaluating a model's plasticity and improving plasticity adaptively for a new task. In this work, we propose a new method, called adaptive plasticity improvement (API), for continual learning. Besides the ability to overcome CF on old tasks, API also tries to evaluate the model's plasticity and then adaptively improve the model's plasticity for learning a new task if necessary. Experiments on several real datasets show that API can outperform other state-of-the-art baselines in terms of both accuracy and memory usage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grid4D: 4D decomposed hash encoding for high-fidelity dynamic Gaussian splatting 24

Grid4D: 4D decomposed hash encoding for high-fidelity dynami...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiawei Xu Zexin Fan Jian Yang Jij Xie PCA Lab VCIP College of Computer Science Nankai University State Key Laboratory for Novel Software Technology Nanjing University Nanjing China and School of Intelligence Science and Technology Nanjing University Suzhou China

ISBN: (纸本)9798331314385

Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene rendering models. However, plane-based methods rely on the inappropriate low-rank assumption and excessively decompose the space-time 4D encoding, resulting in overmuch feature overlap and unsatisfactory rendering quality. To tackle these problems, we propose Grid4D, a dynamic scene rendering model based on Gaussian splatting and employing a novel explicit encoding method for the 4D input through the hash encoding. Different from plane-based explicit representations, we decompose the 4D encoding into one spatial and three temporal 3D hash encodings without the low-rank assumption. Additionally, we design a novel attention module that generates the attention scores in a directional range to aggregate the spatial and temporal features. The directional attention enables Grid4D to more accurately fit the diverse deformations across distinct scene components based on the spatial encoded features. Moreover, to mitigate the inherent lack of smoothness in explicit representation methods, we introduce a smooth regularization term that keeps our model from the chaos of deformation prediction. Our experiments demonstrate that Grid4D significantly outperforms the state-of-the-art models in visual quality and rendering speed. Project page: https://***/Grid4D-web/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation

arXiv

引用

arXiv 2025年

作者： Chen, Kai Li, Xinfeng Yang, Tianpei Wang, Hewei Dong, Wei Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China Nanyang Technological University Singapore School of Computer Science Carnegie Mellon University United States

Large Language Models (LLMs) have made significant progress in various fields. However, challenges remain in Multi-Disciplinary Team (MDT) medical consultations. Current research enhances reasoning through role assignment, task decomposition, and accumulation of medical experience. Multi-role collaboration in MDT consultations often results in excessively long dialogue histories. This increases the model’s cognitive burden and degrades both efficiency and accuracy. Some methods only store treatment histories. They do not extract effective experience or reflect on errors. This limits knowledge generalization and system evolution. We propose a multi-agent MDT medical consultation framework based on LLMs to address these issues. Our framework uses consensus aggregation and a residual discussion structure for multi-round consultations. It also employs a Correct Answer Knowledge Base (CorrectKB) and a Chain-of-Thought Knowledge Base (ChainKB) to accumulate consultation experience. These mechanisms enable the framework to evolve and continually improve diagnosis rationality and accuracy. Experimental results on the MedQA and PubMedQA datasets demonstrate that our framework achieves accuracies of 90.1% and 83.9%, respectively, and that the constructed knowledge bases generalize effectively across test sets from both datasets. Our code is publicly available at: https://***/MDTeamGPT. © 2025, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Loss decoupling for task-agnostic continual learning 23

Loss decoupling for task-agnostic continual learning

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yan-Shuo Liang Wu-Jun Li National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University P. R. China

Continual learning requires the model to learn multiple tasks in a sequential order. To perform continual learning, the model must possess the abilities to maintain performance on old tasks (stability) and adapt itself to learn new tasks (plasticity). Task-agnostic problem in continual learning is a challenging problem, in which task identities are not available in the inference stage and hence the model must learn to distinguish all the classes in all the tasks. In task-agnostic problem, the model needs to learn two new objectives for learning a new task, including distinguishing new classes from old classes and distinguishing between different new classes. For task-agnostic problem, replay-based methods are commonly used. These methods update the model with both saved old samples and new samples for continual learning. Most existing replay-based methods mix the two objectives in task-agnostic problem together, inhibiting the models from achieving a good trade-off between stability and plasticity. In this paper, we propose a simple yet effective method, called loss decoupling (LODE), for task-agnostic continual learning. LODE separates the two objectives for the new task by decoupling the loss of the new task. As a result, LODE can assign different weights for different objectives, which provides a way to obtain a better trade-off between stability and plasticity than those methods with coupled loss. Experiments show that LODE can outperform existing state-of-the-art replay-based methods on multiple continual learning datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Li, Shumeng Qi, Lei Yu, Qian Huo, Jing Shi, Yinghuan Gao, Yang Nanjing University State Key Laboratory for Novel Software Technology China Nanjing University National Institute of Healthcare Data Science China School of Computer Science and Engineering China Shandong Women's University School of Data and Computer Science China

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Stitching, Fine-tuning, and Re-training (SFR). The current fine-tuning approaches mostly involve 2D slice-wise fine-tuning that disregards the contextual information between adjacent slices. Our stitching strategy mitigates the mismatch between natural and 3D medical images. The stitched images are then used for fine-tuning SAM, providing robust initialization of pseudo-labels. Afterwards, we train a 3D semi-supervised segmentation model while maintaining the same parameter size as the conventional segmenter such as V-Net. Our SFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods. We also develop an extended framework SFR+ with selective fine-tuning and re-training through confidence estimation. Extensive experiments validate that our SFR and SFR+ achieve significant improvements in both moderate annotation and scarce annotation across five datasets. In particular, SFR framework improves the Dice score of Mean Teacher from 29.68% to 74.40% with only one labeled data of LA dataset. The code is available at https://***/ShumengLI/SFR. © 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

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：