检索结果-内蒙古大学图书馆

Visual Class Incremental Learning with Textual Priors Guidance based on an Adapted Vision-Language Model

IEEE Transactions on Multimedia 2025年

作者： Zhang, Wentao Yu, Tong Wang, Ruixuan Xie, Jianhui Trucco, Emanuele Zheng, Wei-Shi Yang, Xiaobo Sun Yat-sen Univerisity School of Computer Science and Engineering Guangzhou510275 China Peng Cheng Laboratory Shenzhen518066 China MOE Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou510275 China Second Affiliated Hospital Guangzhou University of Chinese Medicine State Key Laboratory of Dampness Syndrome of Chinese Medicine Guangzhou510260 China Guangdong Provincial Key Laboratory of Clinical Research on Traditional Chinese Medicine Syndrome Guangzhou510120 China University of Dundee School of Science and Engineering DundeeDD1 4HN United Kingdom

An ideal artificial intelligence (AI) system should have the capability to continually learn like humans. However, when learning new knowledge, AI systems often suffer from catastrophic forgetting of old knowledge. Although many continual learning methods have been proposed, they often ignore the issue of misclassifying similar classes and make insufficient use of textual priors of visual classes to improve continual learning performance. In this study, we propose a continual learning framework based on a pre-trained vision-language model (VLM) that does not require storing old class data. This framework utilizes parameter-efficient fine-tuning of the VLM's text encoder for constructing a shared and consistent semantic textual space throughout the continual learning process. The textual priors of visual classes are encoded by the adapted VLM's text encoder to generate discriminative semantic representations, which are then used to guide the learning of visual classes. Additionally, fake out-of-distribution (OOD) images constructed from each training image further assist in the learning of visual classes. Extensive empirical evaluations on three natural datasets and one medical dataset demonstrate the superiority of the proposed framework. The source code is available at https://***/OpenMedIA/CIL_Adapterd_VLM. © 1999-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Cerebrovascular segmentation from mesoscopic optical images using Swin Transformer

引用

Journal of Innovative Optical Health Sciences 2023年第4期16卷 120-133页

作者： Yuxin Li Qianlong Zhang Hang Zhou Junhuai Li Xiangning Li Anan Li Shaanxi Key Laboratory for Network Computing and Security Technology School of Computer Science and Engineering Xi'an University of Technology Xi'an 710048P.R.China School of Computer Science Chengdu University of Information Technology Chengdu 610225P.R.China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics MoE Key Laboratory for Biomedical Photonics Huazhong University of Science and Technology Wuhan 430074 P.R.China HUST-Suzhou Institute for Brainsmatics Suzhou 215123 P.R.China

Vascular segmentation is a crucial task in biomedical image processing,which is significant for analyzing and modeling vascular networks under physiological and pathological *** advances in fluorescent labeling and mesoscopic optical techniques,it has become possible to map the whole-mouse-brain vascular networks at capillary ***,segmenting vessels from mesoscopic optical images is a challenging *** problems,such as vascular signal discontinuities,vessel lumens,and background fluorescence signals in mesoscopic optical images,belong to global semantic information during vascular *** vascular segmentation methods based on convolutional neural networks(CNNs)have been limited by their insufficient receptive fields,making it challenging to capture global semantic information of vessels and resulting in inaccurate segmentation ***,we propose SegVesseler,a vascular segmentation method based on Swin *** adopts 3D Swin Transformer blocks to extract global contextual information in 3D *** approach is able to maintain the connectivity and topology of blood vessels during *** evaluated the performance of our method on mouse cerebrovascular datasets generated from three different labeling and imaging *** experimental results demonstrate that the segmentation effect of our method is significantly better than traditional CNNs and achieves state-of-the-art performance.

关键词： Vascular segmentation Swin Transformer mesoscopic optical imaging fMOST

来源：评论

学校读者我要写书评

暂无评论

A Robust and Generalized Gauss-Seidel Solver for Physically-Correct Simultaneous Collisions

引用

Proceedings of the ACM on Computer Graphics and Interactive Techniques 2025年第1期8卷 1-17页

作者： Huanbo Zhou Zhenyu Xu Xijun Liu Xinyu Zhang Software Engineering Institute East China Normal University Shanghai Shanghai China East China Normal University Shanghai Shanghai China Software Engineering Institute East China Normal University Shanghai Shanghai China Shanghai Key Laboratory of Trustworthy Computing Shanghai Shanghai China and Engineering Research Center of Software/Hardware Co-design Technology and Application MoE) Shanghai Shanghai China

Simulating multi-object collisions in real-time environments remains a significant challenge, particularly when handling simultaneous collisions in a physically accurate manner. Traditional Gauss-Seidel solvers, widely employed in physics engines, often fail to preserve the symmetry and consistency of multi-object interactions that are often observed in physics. In this paper, we present a generalized and robust Gauss-Seidel solver to overcome the difficulties in simultaneous collisions. Using spatial and temporal collision states to classify and resolve constraints, our algorithm ensures correct collision propagation and symmetry, addressing the limitations commonly found in existing solvers. Moreover, our algorithm can mitigate jitters caused by floating-point errors, ensuring smooth and stable collision responses. Our approach demonstrates fast convergence and improved accuracy in scenarios involving complex multi-object collisions.

关键词： Physically-based simulation Gauss-Seidel solver Simultaneous collisions

来源：评论

学校读者我要写书评

暂无评论

Region Attention Fine-tuning with CLIP for Few-shot Classification

Region Attention Fine-tuning with CLIP for Few-shot Classifi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Guangxing Wu Junxi Chen Qiu Li Wentao Zhang Wei-Shi Zheng Ruixuan Wang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China China United Network Communications Corporation Limited Guangdong Branch Guangzhou China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

With the advancements in visual language models such as CLIP and their strong performance in zero-shot recognition, numerous CLIP-based methods have emerged in the field of few-shot classification. However, many of them do not fully leverage the abundant feature information within the CLIP visual encoder and overlook the issue of varying region-specific importance for image classification across different datasets. To address these limitations, we present an attention pooling-based framework for few-shot fine-tuning. Our framework enables the model to learn task-specific attention weights for image regions, while also incorporating background features and a consistency constraint to enhance training. As a result, our approach outperforms the state-of-the-art approaches on 11 benchmarks, demonstrating its effectiveness.

关键词： Training Visualization Benchmark testing Image classification

来源：评论

学校读者我要写书评

暂无评论

On Underdamped Nesterov’s Acceleration

arXiv

引用

arXiv 2023年

作者： Chen, Shuo Shi, Bin Yuan, Ya-Xiang State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

The high-resolution differential equation framework has been proven to be tailor-made for Nesterov’s accelerated gradient descent method (NAG) and its proximal correspondence — the class of faster iterative shrinkage thresholding algorithms (FISTA). However, the systems of theories is not still complete, since the underdamped case (r γ or the iteration kγ in the mixed term. When the momentum parameter r is 2, the new Lyapunov functions are identical to the previous ones. These new proofs do not only include the convergence rate of the objective value previously obtained according to the low-resolution differential equation framework but also characterize the convergence rate of the minimal gradient norm square. All the convergence rates obtained for the underdamped case are continuously dependent on the parameter r. In addition, it is observed that the high-resolution differential equation approximately simulates the convergence behavior of NAG for the critical case r = −1, while the low-resolution differential equation degenerates to the conservative Newton’s equation. The high-resolution differential equation framework also theoretically characterizes the convergence rates, which are consistent with that obtained for the underdamped case with r = −1. © 2023, CC BY-SA.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

一种含Tröger碱单元的AIE分子的独特力致荧光增强行为

引用

Science China Materials 2023年第5期66卷 1959-1967页

作者：倪珏宸臧启光张浩可孙景志唐本忠 MOE Key Laboratory of Macromolecules Synthesis and Functionalization Department of Polymer Science and EngineeringZhejiang UniversityHangzhou 310027China Center of Healthcare Materials Shaoxing InstituteZhejiang UniversityShaoxing 312000China ZJU-Hangzhou Global Scientific and Technological Innovation Center Hangzhou 311215China Shenzhen Institute of Aggregate Science and Technology School of Science and EngineeringThe Chinese University of Hong KongShenzhen 518172China

本文报道了一种性能独特的聚集诱导发光分子DTPE-TB,它由位于中间的一个Tröger碱和两端的两个四苯基乙烯(TPE)基团构成.当DTPE-TB分子固体受到机械力作用时,Tröger碱的A-型结构通过改变二面角发生形变承载外力,使分子内运动... 详细信息

本文报道了一种性能独特的聚集诱导发光分子DTPE-TB,它由位于中间的一个Tröger碱和两端的两个四苯基乙烯(TPE)基团构成.当DTPE-TB分子固体受到机械力作用时,Tröger碱的A-型结构通过改变二面角发生形变承载外力,使分子内运动受限加重,固体荧光增强.而TPE基团受力很小,其排列方式基本不变,所以发光波长仅有微小移动.我们将这种特殊的力致发光变色效应命名为力致荧光增强.

关键词： aggregation-induced emission mechano-induced emission enhancement dihedral angle Λ-shaped configuration Tröger’s base

来源：评论

学校读者我要写书评

暂无评论

Taking Myopic Best Response Against The Hedge Algorithm

Taking Myopic Best Response Against The Hedge Algorithm

引用

第42届中国控制会议

作者： Xinxiang Guo Yifen Mu School of Mathematical Sciences University of Chinese Academy of Sciences The State Key Laboratory of Scientific and Engineering Computing Academy of Mathematics and Systems ScienceChinese Academy of Sciences The Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of Sciences

With the rapid development of artificial intelligence(AI),the game between the human and machine/AI becomes more and more *** related theoretical analysis becomes significant and necessary,which however is still *** problem involves evolution analysis and optimal control of dynamic game systems driven by learning *** this paper,we consider a finitely repeated two-player zero-sum *** study the dynamic evolution process of the game system,in which one player employs the Hedge algorithm and the other player takes the myopic best *** the updating formula of the Hedge algorithm,we define a quantity called the state and construct the State Transition Triangle Graph(STTG).Then,we prove that the game system is periodic after o(T) stages.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time Monocular 3D Pose Tracking for Non-cooperative Spacecraft in Close Range

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Tang, Hao Liu, Chang Liu, Jia Zhang, Pandeng Hu, Weiduo Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen China Shenzhen Key Laboratory for Exascale Engineering and Scientific Computing Shenzhen China University of Chinese Academy of Sciences Beijing China Beihang University School of Astronautics Beijing China

Real-time pose tracking for noncooperative spacecraft is crucial for numerous space missions, such as debris removal and docking. Existing pose tracking methods either suffer from shadow occlusion and cluttered backgrounds in space or lack computational efficiency. This study proposes a real-time system for tracking the 6-degree-of-freedom pose of a noncooperative spacecraft for proximity operations using a single calibrated camera. The proposed method parameterizes the pose in the Lie group of SE(3) and exploits the 3D boundaries and 3D contour, which are automatically extracted from the 3D model of the spacecraft as geometric features (GFs). At each frame of the tracking process, the initial pose is predicted using an error state Kalman filter (ESKF). Using the initial pose, the tracking system searches the input image for the 2D edge points that are associated with the 3D GFs based on a conditional random field and then rapidly determines the spacecraft pose in SE(3) by minimizing the distances of the projected 3D GFs to their corresponding 2D edge points using the M-estimation and Newton’s method. The covariance of the optimized pose is estimated based on the Karush–Kuhn–Tucker condition for pose optimization. With the estimated pose covariance, the ESKF is developed based on second-order autoregression in SE(3) to produce the maximum a posteriori estimate of the pose and initialize the pose tracking at the next frame. A sufficient number of synthetic and real trials indicate that the proposed method outperforms the existing methods in terms of accuracy and efficiency. The experimental results reveal that the proposed method achieves a rotation angle error of approximately 0.5° and relative position error of approximately 0.6% and that the average runtime of the proposed method is approximately 0.02 seconds per frame. © 1963-2012 IEEE.

关键词： Computational geometry

来源：评论

学校读者我要写书评

暂无评论

Quantum simulation of a class of highly-oscillatory transport equations via Schrödingerisation

arXiv

引用

arXiv 2025年

作者： Gu, Anjiao Jin, Shi School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China Institute of Natural Sciences Shanghai Jiao Tong University Shanghai200240 China Ministry of Education Key Laboratory in Scientific and Engineering Computing Shanghai200240 China

In this paper, we present quantum algorithms for a class of highly-oscillatory transport equations, which arise in semiclassical computation of surface hopping problems and other related non-adiabatic quantum dynamics, based on the Born-Oppenheimer approximation. Our method relies on the classical nonlinear geometric optics method, and the recently developed Schrödingerisation approach for quantum simulation of partial differential equations. The Schrödingerisation technique can transform any linear ordinary and partial differential equations into Hamiltonian systems evolving under unitary dynamics, via a warped phase transformation that maps these equations to one higher dimension. We study possible paths for better recoveries of the solution to the original problem by shifting the bad eigenvalues in the Schrödingerized system. Our method ensures the uniform error estimates independent of the wave length, thus allowing numerical accuracy, in maximum norm, even without numerically resolving the physical oscillations. Various numerical experiments are performed to demonstrate the validity of this approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases

arXiv

引用

arXiv 2023年

作者： Zhang, Wentao Huang, Yujun Zhang, Tong Zou, Qingsong Zheng, Wei-Shi Wang, Ruixuan School of Computer Science and Engineering Sun Yat-sen Univerisity Guangzhou China Peng Cheng Laboratory Shenzhen China Guangdong Province Key Laboratory of Computational Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China

Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge. To address the catastrophic forgetting issue, an Adapter-based Continual Learning framework called ACL is proposed to help effectively learn a set of new diseases at each round (or task) of continual learning, without changing the shared feature extractor. The learnable lightweight task-specific adapter(s) can be flexibly designed (e.g., two convolutional layers) and then added to the pretrained and fixed feature extractor. Together with a specially designed task-specific head which absorbs all previously learned old diseases as a single ‘out-of-distribution’ category, task-specific adapter(s) can help the pretrained feature extractor more effectively extract discriminative features between diseases. In addition, a simple yet effective fine-tuning is applied to collaboratively fine-tune multiple task-specific heads such that outputs from different heads are comparable and consequently the appropriate classifier head can be more accurately selected during model inference. Extensive empirical evaluations on three image datasets demonstrate the superior performance of ACL in continual learning of new diseases. The source code is available at https: //***/GiantJun/CL_Pytorch. Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

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：