检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

ISBN: (纸本)157735897X

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis

arXiv

引用

arXiv 2025年

作者： Che, Haoxuan Wu, Yifei Jin, Haibo Xia, Yong Chen, Hao Department of Computer Science and Engineering Hong Kong University of Science and Technology University Hong Kong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Department of Computer Science and Engineering Department of Chemical and Biological Engineering Division of Life Science Hong Kong University of Science and Technology Hong Kong

Federated domain generalization aims to train a global model from multiple source domains and ensure its generalization ability to unseen target domains. Due to the target domain being with unknown domain shifts, attempting to approximate these gaps by source domains may be the key to improving model generalization capability. Existing works mainly focus on sharing and recombining local domain-specific attributes to increase data diversity and simulate potential domain shifts. However, these methods may be insufficient since only the local attribute recombination can be hard to touch the out-of-distribution of global data. In this paper, we propose a simple-yet-efficient framework named Federated Domain Adversarial Generation (FedDAG). It aims to simulate the domain shift and improve the model generalization by adversarially generating novel domains different from local and global source domains. Specifically, it generates novel-style images by maximizing the instance-level feature discrepancy between original and generated images and trains a generalizable task model by minimizing their feature discrepancy. Further, we observed that FedDAG could cause different performance improvements for local models. It may be due to inherent data isolation and heterogeneity among clients, exacerbating the imbalance in their generalization contributions to the global model. Ignoring this imbalance can lead the global model’s generalization ability to be sub-optimal, further limiting the novel domain generation procedure. Thus, to mitigate this imbalance, FedDAG hierarchically aggregates local models at the within-client and across-client levels by using the sharpness concept to evaluate client model generalization contributions. Extensive experiments across four medical benchmarks demonstrate FedDAG’s ability to enhance generalization in federated medical scenarios. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Regression coefficient estimation from remote sensing maps

arXiv

引用

arXiv 2024年

作者： Lu, Kerri Kluger, Dan M. Bates, Stephen Wang, Sherrie Laboratory for Information and Decision Systems MIT United States Department of Electrical Engineering and Computer Science MIT United States Department of Mechanical Engineering MIT United States Institute for Data Systems and Society MIT United States

Remote sensing map products are used to estimate regression coefficients relating environmental variables, such as the effect of conservation zones on deforestation. However, the quality of map products varies, and — because maps are outputs of complex machine learning algorithms that take in a variety of remotely sensed variables as inputs — errors are difficult to characterize. Thus, population-level estimates from such maps may be biased. In this paper, we apply prediction-powered inference (PPI) to regression coefficient estimation. PPI generates unbiased estimates by using a small amount of randomly sampled ground truth data to correct for bias in large-scale remote sensing map products. Applying PPI across multiple remote sensing use cases in regression coefficient estimation, we find that it results in estimates that are (1) more reliable than using the map product as if it were 100% accurate and (2) have lower uncertainty than using only the ground truth and ignoring the map product. Empirically, we observe effective sample size increases of up to 17-fold using PPI compared to only using ground truth data. This is the first work to estimate remote sensing regression coefficients without assumptions on the structure of map product errors. data and code are available at https://***/Earth-Intelligence-Lab/ uncertainty-quantification. © 2024, CC BY.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification 39

Infer the Whole from a Glimpse of a Part: Keypoint-Based Kno...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lv, Kai Li, Yunlong Chen, Zhuo Wang, Shuo Han, Sheng Lin, Youfang School of Computer Science & Technology Beijing Jiaotong University China Beijing Key Laboratory of Traffic Data Mining Embodied Intelligence China Zhejiang University China CSSC Intelligent Innovation Research Institute China CSSC Systems Engineering Research Institute China

ISBN: (纸本)157735897X

Vehicle re-identification aims to match vehicles across non-overlapping camera views. Many existing methods extract features from one specific image, and these methods lack view-invariance when comparing vehicles of different orientations. As a result, discriminative parts obscured by viewpoint changes cannot contribute effectively to matching. This work presents a novel keypoint-based framework for vehicle Re-ID. We propose to explicitly model the intrinsic structural relationships between vehicle components via knowledge graph. By establishing connection between keypoints, our approach aims to leverage such prior to match vehicles even when some parts are not directly comparable due to orientation inconsistencies. Specifically, given query and gallery images, we first detect visible keypoints. Then, a transformer-based model infers features for non-overlapped keypoints by conditioning on visible correspondences defined in the knowledge graph. The final representation integrates visible and inferred features. Extensive experiments demonstrate our method outperforms state-of-the-arts on standard benchmarks under cross-view matching scenarios. To our knowledge, this is the first work introducing structural priors via keypoint knowledge graphs for view-invariant vehicle re-identification. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering 39

SCANS: Mitigating the Exaggerated Safety for LLMs via Safety...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cao, Zouying Yang, Yifei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)157735897X

Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs tend to reject benign queries due to the exaggerated safety issue, limiting their helpfulness. In this paper, we propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns in aligned LLMs. First, SCANS extracts the refusal steering vectors within the activation space and utilizes vocabulary projection to anchor some specific safety-critical layers which influence model refusal behavior. Second, by tracking the hidden state transition, SCANS identifies the steering direction and steers the model behavior accordingly, achieving a balance between exaggerated safety and adequate safety. Experiments show that SCANS achieves new state-of-the-art performance on XSTest and OKTest benchmarks, without impairing their defense capability against harmful queries and maintaining almost unchanged model capability. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attribute Reduction Method Based on Improved Granular Ball Neighborhood Rough Set 7

Attribute Reduction Method Based on Improved Granular Ball N...

引用

7th International Conference on Cloud Computing and Big data Analytics, ICCCBDA 2022

作者： Xia, Han Chen, Zizhong Wu, Yanmin Qi, Jinli Chongqing Key Laboratory of Computer Science and Technology Chongqing University of Posts and Telecommunications ChongQing China ChongQing College of Electronic Engineering Department of Artificial Intelligence and Big Data ChongQing China ChongQing College of Electronic Engineering Department of General Education and International Studies ChongQing China

ISBN: (纸本)9781665487115

Feature reduction is an important aspect of big data analytics today, and neighborhood rough set is a classic attribute reduction method. The traditional neighborhood rough set finds out the radius suitable for problem solving by specifying the radius of the neighborhood or using a grid search method. There are a lot of overlapping calculations in the neighborhood calculation, and the calculation complexity is high. The granular ball neighbor-hood rough set can adaptively generate different neighborhood radius, and obtains better algorithm efficiency and learning effect than the traditional neighborhood rough set. However, due to the overlap problem in the process of granular ball generation, the granular ball neighborhood rough set still exists the overlap calculation of neighborhoods. For this reason, this paper solves the problem of granular ball overlap by detecting heterogeneous ball overlap and splitting, and thus designs an improved granular ball neighbor-hood rough set attribute reduction method. Experiments show that the improved granular ball neighborhood rough set has higher classification accuracy on the public benchmark dataset than the classic neighborhood rough set and the standard granular ball neighborhood rough set. © 2022 IEEE.

关键词： Cloud computing Costs Search methods Rough sets Big data Benchmark testing Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Zongyuan Duan, Tianyang Lin, Zheng Huang, Dong Fang, Zihan Sun, Zekai Xiong, Ling Liang, Hongbin Cui, Heming Cui, Yong Department of Computer Science The University of Hong Kong Hong Kong Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Computer Science City University of Hong Kong Hong Kong School of Computer and Software Engineering Xihua University Chengdu610039 China National United Engineering Laboratory of Integrated and Intelligent Transportation The National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Department of Computer Science and Technology Ts-inghua University Beijing100084 China

Recently, deep reinforcement learning (DRL) has emerged as a promising approach for robotic control. However, the deployment of DRL in real-world robots is hindered by its sensitivity to environmental perturbations. While existing white-box adversarial attacks rely on local gradient information and apply uniform perturbations across all states to evaluate DRL robustness, they fail to account for temporal dynamics and state-specific vulnerabilities. To combat the above challenge, we first conduct a theoretical analysis of white-box attacks in DRL by establishing the adversarial victim-dynamics Markov decision process (AVD-MDP), to derive the necessary and sufficient conditions for a successful attack. Based on this, we propose a selective state-aware reinforcement adversarial attack method, named STAR, to optimize perturbation stealthiness and state visitation dispersion. STAR first employs a soft mask-based state-targeting mechanism to minimize redundant perturbations, enhancing stealthiness and attack effectiveness. Then, it incorporates an information-theoretic optimization objective to maximize mutual information between perturbations, environmental states, and victim actions, ensuring a dispersed state-visitation distribution that steers the victim agent into vulnerable states for maximum return reduction. Extensive experiments demonstrate that STAR outperforms state-of-the-art benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Thermal conductivity prediction with Fully Connected Neural Network 3

Thermal conductivity prediction with Fully Connected Neural ...

引用

3rd International Conference on Artificial Intelligence, Information Processing and Cloud Computing, AIIPCC 2022

作者： Zhang, Xingxing Li, Shaobo Yu, Liya Dong, Rongzhi Song, Qisong Wang, Zhongyu State Key Laboratory of Public Big Data Guizhou University Guiyang China College of Mechanical Engineering Guizhou University Guiyang China Department of Computer Science and Engineering University of South Carolina SC United States Guizhou University Guiyang China

ISBN: (纸本)9783800759330

In this paper a Fully Connected Neural Network (FCNN) model is developed for the prediction of the material thermal conductivity. The traditional theoretical experimental research and computational simulation could not meet the needs of scientists' exploration of new materials. In recent years, data-driven machine learning algorithm has been used in material screening and performance prediction. Thermoelectric materials have become a hot topic in the field of materials research because of their ability to realize the interactive conversion of electric energy and thermal energy, small size, light weight, long service life and environmental friendliness. The hypothesis verification method based on a large number of experimental observations and the method of system calculation using the first principle are difficult to meet the requirements for rapid discovery of new materials in the current era due to the long research period. Therefore, the use of machine learning algorithms to assist in the development of new thermoelectric materials is of great significance. In this paper, a material thermal conductivity prediction model based on Fully Connected Neural Network (FCNN) is established, which is applied to the thermal conductivity dataset in the Materials Project database. The model is evaluated by ten-fold cross-verification, and good prediction results are obtained. The mapping model between descriptive and thermal conductivity of materials is established by using machine learning algorithm, which can be used for large-scale material screening and guiding experimental research. © VDE VERLAG GMBH.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

DPP-HSS: Towards Fast and Scalable Hypervolume Subset Selection for Many-objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Gong, Cheng Nan, Yang Shang, Ke Guo, Ping Ishibuchi, Hisao Zhang, Qingfu City University of Hong Kong Department of Computer Science Hong Kong City University of Hong Kong Shenzhen Research Institute Shenzhen China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China

Hypervolume subset selection (HSS) has received significant attention since it has a strong connection with evolutionary multi-objective optimization (EMO), such as environment selection and post-processing to identify representative solutions for decision-makers. The goal of HSS is to find the optimal subset that maximizes the hypervolume indicator subject to a given cardinality constraint. However, existing HSS algorithms or related methods are not efficient in achieving good performance in high-dimensional objective spaces. This is primarily because HSS problems become NP-hard when the number of objectives exceeds two, and the calculation of hypervolume contribution is very time-consuming. To efficiently solve HSS problems while maintaining a good solution quality, we propose a fast and scalable hypervolume subset selection method for many-objective optimization based on the determinantal point process (DPP), named DPP-HSS, which is fully free of hypervolume contribution calculation. Specifically, DPP-HSS constructs a hypervolume kernel matrix by extracting the convergence and diversity representations of each solution for a given HSS problem. This matrix is then used to build a DPP model. Subsequently, the original HSS problem is reformulated as a new maximization optimization problem based on the constructed model. A greedy DPP-based hypervolume subset selection algorithm is implemented to solve this transformed problem. Extensive experiments show that the proposed DPP-HSS achieves significant speedup and good hypervolume performance in comparison with state-of-the-art HSS algorithms on benchmark problems. Furthermore, DPP-HSS demonstrates very good scalability with respect to the number of objectives. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Power-System Economic Dispatching Based on Enhanced Group Search Optimizer 1

引用

18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Pan, Jeng-Shyang Nguyen, Trong-The Nguyen, Trinh-Dong Nguyen, Vinh-Tiep Dao, Thi-Kien College of Computer Science and Engineering Shandong University of Science and Technology Qing-Dao266590 China Department of Information Management Chaoyang University of Technology Taichung41349 Taiwan University of Information Technology Ho Chi Minh City700000 Viet Nam Vietnam National University Ho Chi Minh City700000 Viet Nam Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China

ISBN: (数字)9789819901050

ISBN: (纸本)9789819901043

Economic dispatch (ED) is one of the critical tasks in a power system’s optimization issues, but its characteristics with non-convex, high-dimensional, non-linear, and non-differentiable, so that caused solutions are more challenging in reality. This paper suggests an enhanced group search optimizer (EGSO) for solving the ED model with the valve-point effect and the different fuels. The EGSO adopts the original group search optimizer (GSO) by changing polar to Cartesian coordinate’s conversion and adding cyclic translation operators to the search behavior of the finder and walker to avoid falling into local optimal and slow convergence of the GSO. In the experiment section, the testing power systems of the ED model are used to validate the EGSO performance. The experimental results reveal that EGSO outperformed the other algorithms regarding convergence speed, the time required to complete calculations, and impacts with lower fuel cost. Additionally, with excellent outcomes in optimization issues involving multiple local optimal values show the EGSO is practical, quick, and efficient in addressing the challenging ED model. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

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：