检索结果-内蒙古大学图书馆

19th Conference on Machine Learning in Computational Biology Meeting, MLCB 2024

作者： Hermann, Leon Fiedler, Tobias Nguyen, Hoang An Nowicka, Melania Bartoszewicz, Jakub M. Hasso Plattner Institute Digital Engineering Faculty University of Potsdam Germany Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology United States

Pretrained protein language models are becoming increasingly popular as a backbone for protein property inference tasks such as structure prediction or function annotation, accelerating biological research. However, related research oftentimes does not consider the effects of data leakage from pretraining on the actual downstream task, resulting in potentially unrealistic performance estimates. Reported generalization might not necessarily be reproducible for proteins highly dissimilar from the pretraining set. In this work, we measure the effects of data leakage from protein language model pretraining in the domain of protein thermostability prediction. Specifically, we compare two different dataset split strategies: a pretraining-aware split, designed to avoid similarity between pretraining data and the held-out test sets, and a commonly-used naive split, relying on clustering the training data for a downstream task without taking the pretraining data into account. Our experiments suggest that data leakage from language model pretraining shows consistent effects on melting point prediction across all experiments, distorting the measured performance by an average 11.1% compared to the pretraining-aware split. The source code and our dataset splits are available at https://***/dacshpi/pretraining-aware-hotprot. © 2024 Proceedings of Machine Learning Research. All rights reserved.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

OGSOD-2.0: A Challenging Multi-Modal Benchmark for Optical-SAR Object Detection 16

OGSOD-2.0: A Challenging Multi-Modal Benchmark for Optical-S...

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Ruan, Rui Yang, Kai Zhao, Zhicheng Li, Chenglong Tang, Jin School of Internet Anhui University Hefei230601 China Anhui Provincial Key Laboratory of Security Artificial Intelligence China School of Computer Science and Technology Anhui University Hefei230601 China School of Artificial Intelligence Anhui University Hefei230601 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

With the development of the rapid development of satellite technology, multi-modal object detection between optical and SAR (Synthetic Aperture Radar) images has attracted growing interest in the field of remote sensing image interpretation. However, this area lacks a dataset that considers novel and diverse challenges related to practical applications, crucial for both the training and evaluation of recent detectors. In this paper, we introduce a new challenging multi-modal dataset for optical-SAR object detection, OGSOD-2.0, aiming to enhance object detection in tiny-scale and crowded objects under complex backgrounds. Building on OGSOD-1.0, the proposed dataset supplements more 5,130 optical-SAR image pairs from the Sentinel satellite series with 24,421 instance annotations, containing four significant types of static objects: bridges, harbors, oil tanks, and playgrounds. These objects exhibit a wide variety of scales, aspect ratios, and orientations under complex aerial scenarios. Specially, most objects are characterized by relatively low resolution, even smaller than 12 pixels, and clustered together at high densities, further increasing the challenges for existing detection methods. To evaluate the challenging aspects of OGSOD-2.0, we compare our proposed dataset with existing optical-SAR datasets over several state-of-the-art methods including single-modal, cross-modal and multi-modal detectors. Comprehensive experiments show that proposed OGSOD-2.0 are quite challenging and related to practical applications. This multi-modal benchmark will be publicly available. © 2025 SPIE.

关键词： Oil tanks

来源：评论

学校读者我要写书评

暂无评论

Toward Correlated Sequential Rules

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2024年第10期5卷 5340-5351页

作者： Chen, Lili Gan, Wensheng Chen, Chien-Ming Tongji University Department of Computer Science and Technology Shanghai200082 China Jinan University College of Cyber Security Guangzhou510632 China Pazhou Laboratory Guangzhou510330 China Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing210044 China

The goal of high-utility sequential pattern mining (HUSPM) is to efficiently discover profitable or useful sequential patterns in a large number of sequences. However, simply being aware of utility-eligible patterns is insufficient for making predictions. To compensate for this deficiency, high-utility sequential rule mining (HUSRM) is designed to explore the confidence or probability of predicting the occurrence of consequence sequential patterns based on the appearance of premise sequential patterns. It has numerous applications, such as product recommendation and weather prediction. However, the existing algorithm, known as HUSRM, is limited to extracting all eligible rules while neglecting the correlation between the generated sequential rules. To address this issue, we propose a novel algorithm called correlated high-utility sequential rule miner (CoUSR) to integrate the concept of correlation into HUSRM. The proposed algorithm requires not only that each rule be correlated but also that the patterns in the antecedent and consequent of the high-utility sequential rule be correlated. The algorithm adopts a utility-list structure to avoid multiple database scans. Additionally, several pruning strategies are used to improve the algorithm's efficiency and performance. Based on several real-world datasets, subsequent experiments demonstrated that CoUSR is effective and efficient in terms of operation time and memory consumption. All codes are accessible on GitHub: https://***/DSI-Lab1/CoUSR. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

User Satisfaction-Aware Edge Computation Offloading in 5G Multi-Scenario

引用

Journal of Communications and Information Networks 2023年第3期8卷 271-282页

作者： Xiaochuan Sun Xiaoyu Niu Yutong Wang Yingqi Li College of Artificial Intelligence North China University of Science and TechnologyTangshan 063210China Hebei Key Laboratory of Industrial Intelligent Perception Tangshan 063210China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

Edge computation offloading has made some progress in the fifth generation mobile network(5G).However,load balancing in edge computation offloading is still a challenging ***,with the continuous pursuit of low execution latency in 5G multi-scenario,the functional requirements of edge computation offloading are further *** the above challenges,we raise a unique edge computation offloading method in 5G multi-scenario,and consider user *** method consists of three functional parts:offloading strategy generation,offloading strategy update,and offloading strategy ***,the offloading strategy is generated by means of a deep neural network(DNN),then update the offloading strategy by updating the DNN ***,we optimize the offloading strategy based on changes in user *** summary,compared to existing optimization methods,our proposal can achieve performance close to the *** simulation results indicate the latency of the execution of our method on the CPU is under 0.1 seconds while improving the average computation rate by about 10%.

关键词： DNN user satisfaction 5G multi-scenario edge computation offloading

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Self-Perception Enhanced Large Language Model for 3D Region-of-Interest Captioning With Limited Data

引用

IEEE Transactions on Multimedia 2025年 27卷 2935-2948页

作者： Shi, Lu Kan, Shichao Jin, Yi Zhang, Linna Cen, Yigang Bejing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation School of Computer Science and Technology Visual Intellgence + X International Cooperation Joint Laboratory of MOE Beijing100044 China Central South University School of Computer Science and Engineering Changsha410083 China Beijing Jiaotong University Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education and the School of Computer Science and Technology Beijing100044 China Guizhou University School of Mechanical Engineering Guiyang550025 China

3D Region-of-Interest (RoI) Captioning involves translating a model's understanding of specific objects within a complex 3D scene into descriptive captions. Recent advancements in Large Language Models (LLMs) have shown great potential in this area. Existing methods capture the visual information from RoIs as input tokens for LLMs. However, this approach may not provide enough detailed information for LLMs to generate accurate region-specific captions. In this paper, we introduce Self-RoI, a Large Language Model with multi-modal self-perception capabilities for 3D RoI captioning. To ensure LLMs receive more precise and sufficient information, Self-RoI incorporates Implicit Textual Info. Perception to construct a multi-modal vision-language information. This module utilizes a simple mapping network to generate textual information about basic properties of RoI from vision-following response of LLMs. This textual information is then integrated with the RoI's visual representation to form a comprehensive multi-modal instruction for LLMs. Given the limited availability of 3D RoI-captioning data, we propose a two-stage training strategy to optimize Self-RoI efficiently. In the first stage, we align 3D RoI vision and caption representations. In the second stage, we focus on 3D RoI vision-caption interaction, using a disparate contrastive embedding module to improve the reliability of the implicit textual information and employing language modeling loss to ensure accurate caption generation. Our experiments demonstrate that Self-RoI significantly outperforms previous 3D RoI captioning models. Moreover, the Implicit Textual Info. Perception can be integrated into other multi-modal LLMs for performance enhancement. We will make our code available for further research. © 1999-2012 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Retrieval-and-alignment based large-scale indoor point cloud semantic segmentation

引用

science China(Information sciences) 2024年第4期67卷 164-180页

作者： Zongyi XU Xiaoshui HUANG Bo YUAN Yangfu WANG Qianni ZHANG Weisheng LI Xinbo GAO School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing Institute for Brain and Intelligence Guangyang Bay Laboratory Shanghai Artificial Intelligence Laboratory School of Electronic Engineering and Computer Science Queen Mary University of London

Current methods for point cloud semantic segmentation depend on the extraction of descriptive features. However, unlike images, point clouds are irregular and often lack texture information, making it demanding to extract discriminative features. In addition, noise, outliers, and uneven point distribution are commonly present in point clouds, which further complicates the segmentation task. To address these problems, a novel architecture is proposed for direct and accurate large-scale point cloud segmentation based on point cloud retrieval and alignment. The proposed approach involves using a feature-based point cloud retrieval method for searching for reference point clouds with annotations from a dataset. In the following segmentation stage, an overlap-based point cloud registration method has been developed to align the target and reference point clouds. For accurate and robust alignment, an overlap region estimation module is trained to locate the optimal overlap region between two pieces of point clouds in a coarse-to-fine manner. In the detected overlap region, the global and local features of the points are extracted and combined for featuremetric registration to obtain accurate transformation parameters between the target and reference point clouds. After alignment, the annotated segmentation of the reference is transferred to the target point clouds to obtain accurate segmentation results. Extensive experiments are conducted to show that the developed method outperforms the state-of-the-art approaches in terms of both accuracy and robustness against noise and outliers.

关键词： point cloud semantic segmentation large-scale indoor point clouds point cloud alignment overlap estimation label transfer

来源：评论

学校读者我要写书评

暂无评论

Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction 38

Long-Tailed Object Detection Pre-training: Dynamic Rebalanci...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Duan, Chen-Long Li, Yong Wei, Xiu-Shen Zhao, Lin Nanjing University of Science and Technology China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University China

Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model parameters, often fall short when confronted with long-tailed distributions, especially in detection tasks. This is largely due to extreme data imbalance and the issue of simplicity bias. In this paper, we introduce a novel pre-training framework for object detection, called Dynamic Rebalancing Contrastive Learning with Dual Reconstruction (2DRCL). Our method builds on a Holistic-Local Contrastive Learning mechanism, which aligns pre-training with object detection by capturing both global contextual semantics and detailed local patterns. To tackle the imbalance inherent in long-tailed data, we design a dynamic rebalancing strategy that adjusts the sampling of underrepresented instances throughout the pre-training process, ensuring better representation of tail classes. Moreover, Dual Reconstruction addresses simplicity bias by enforcing a reconstruction task aligned with the self-consistency principle, specifically benefiting underrepresented tail classes. Experiments on COCO and LVIS v1.0 datasets demonstrate the effectiveness of our method, particularly in improving the mAP/AP scores for tail classes. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards the Identifiability and Explainability for Personalized Learner Modeling: An Inductive Paradigm 24

Towards the Identifiability and Explainability for Personali...

引用

33rd ACM Web Conference, WWW 2024

作者： Li, Jiatong Liu, Qi Wang, Fei Liu, Jiayu Huang, Zhenya Yao, Fangzhou Zhu, Linbo Su, Yu University of Science and Technology of China Anhui Province Key Laboratory of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence Hefei China University of Science and Technology of China School of Computer Science and Technology Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China Hefei Normal University Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China

ISBN: (纸本)9798400701719

Personalized learner modeling using cognitive diagnosis (CD), which aims to model learners' cognitive states by diagnosing learner traits from behavioral data, is a fundamental yet significant task in many web learning services. Existing cognitive diagnosis models (CDMs) follow theproficiency-response paradigm that views learner traits and question parameters as trainable embeddings and learns them through learner performance prediction. However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners' cognitive states and the quality of web learning services. To address these problems, we propose an identifiable cognitive diagnosis framework (ID-CDF) based on a novelresponse-proficiency-response paradigm inspired by encoder-decoder models. Specifically, we first devise the diagnostic module of ID-CDF, which leverages inductive learning to eliminate randomness in optimization to guarantee identifiability and captures the monotonicity between overall response data distribution and cognitive states to prevent explainability overfitting. Next, we propose a flexible predictive module for ID-CDF to ensure diagnosis preciseness. We further present an implementation of ID-CDF, i.e., ID-CDM, to illustrate its usability. Extensive experiments on four real-world datasets with different characteristics demonstrate that ID-CDF can effectively address the problems without loss of diagnosis preciseness. Our code is available at https://***/CSLiJT/ID-CDF. © 2024 ACM.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

WPIA:accelerating DNN warm-up in Web browsers by precompiling WebGL programs

引用

Frontiers of computer science 2024年第6期18卷 281-283页

作者： Deyu TIAN Yun MA Yudong HAN Qi YANG Haochen YANG Gang HUANG Key Laboratory of High Confidence Software Technologies(Peking University) Ministry of EducationSchool of Computer SciencePeking UniversityBeijing 100871China Institute for Artificial Intelligence Peking UniversityBeijing 100871China National Key Laboratory of Data Space Technology and System Beijing 100195China

1 *** the advent of artificial intelligence,it is becoming increasingly common to leverage deep learning technologies to provide intelligent services in Web apps[1].Compared with traditional approaches where deep neural network(DNN)runs at cloud servers,DNN inference in Web browsers avoids serverconnections,boostingtheresponsivenesssand enhancing user privacy of Web apps[2].Typically,GPU acceleration is required during DNN inference,especially on enddevices.

关键词： Web browser WebGL

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：