检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Xuelin Shen Haoqiao Ou Wenhan Yang Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) College of Computer Science and Software Engineering Shenzhen University PengCheng Laboratory

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Among various technical approaches in machine vision coding, Image Coding for Machine (ICM) stands out for its capability to simultaneously fulfill both human perception and machine vision needs. However, it is often criticized for its lack of efficiency regarding rate-analytics performance. In this paper, we propose an Appearance Redundancy Reduction (ARR) module, designed to function as a plug-in for existing ICM frameworks, aiming to further enhance the coding efficiency regarding rate analytics without any changes to the ICM itself. To be specific, our work pays additional attention to the intrinsic correlation between the low-level image structure and high-level vision analytics, and subsequently proposes a novel colour quantization mechanism to squeeze out the analytics-free redundant appearance information. Moreover, a differentiable soften quantization operation is derived to enable end-to-end training within the ICM framework. Extensive experimental results have shown that integrating the proposed ARR module yields substantial improvements regarding rate-analytic performance, even surpassing the performance of the feature coding paradigm, while maintaining the generalizability across different tasks and acceptable perceptual representation.

关键词： Training Image coding Quantization (signal) Correlation Codecs Image color analysis Machine vision

来源：评论

学校读者我要写书评

暂无评论

A Link Simulation Technique for LEO Satellite Constellations in the Electromagnetic Environment 2nd

A Link Simulation Technique for LEO Satellite Constellations...

引用

2nd International Conference on Network Simulation and Evaluation, NSE 2023

作者： Zhang, Yi Wang, Xiaofeng Shen, Taiqian Zhang, Guoxiu School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9789819745180

Link simulation can provide strong support for the verification and evaluation of new techniques for low earth orbit (LEO) satellite constellations. Aiming at the feature that communication links of LEO satellite constellations are susceptible to electromagnetic environment interference (EEI), we propose a link simulation architecture named LEOLS-Stack. To improve usability, scalability and fidelity, the proposed architecture integrates three key techniques: (1) models construction of natural electromagnetic interference, interstellar electromagnetic interference and artificial electromagnetic interference, which can quickly construct scenarios containing different electromagnetic environments;(2) automatic extraction of interference links, which can automatically divide interference links and calculate link performance data;(3) link simulation combining performance data with interference signals, which can identify the characteristics of interference signals and simulate interference links. Experiments show that constellations in different electromagnetic environments can be quickly built by the interference construction and simulation process. At the same time, the fidelity of link simulation under electromagnetic interference is improved. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Signal interference

来源：评论

学校读者我要写书评

暂无评论

Magnetic separation, sunlight-driven photocatalytic activity, and antibacterial studies of Sm-doped Co0.33Mg0.33Ni0.33Fe2O4 nanoparticles

引用

Environmental science and Pollution Research 2024年第24期31卷 35631-35650页

作者： Aridi, Amani Rabaa, Mariam Mezher, Malak Naoufal, Daoud Khalil, Mahmoud I. Awad, Ramadan Chemistry Department Faculty of Science Beirut Arab University Beirut Lebanon Inorganic and Organometallic Coordination Chemistry Laboratory Faculty of Sciences I Lebanese University Hadath Lebanon Department of Biological Sciences Faculty of Science Beirut Arab University Beirut Lebanon Molecular Biology Unit Department of Zoology Faculty of Science Alexandria University Alexandria Egypt Physics Department Faculty of Science Alexandria University Alexandria Egypt Department of Basic Sciences Faculty of Computer Science and Artificial Intelligence Pharos University in Alexandria Alexandria Egypt

Magnetic nanoparticles have emerged as a promising tool for wastewater treatment due to their unique properties. In this regard, Co0.33Mg0.33Ni0.33SmxFe2-xO4 (0.00 ≤x≤ 0.08) nanoparticles were prepared to examine their magnetic separation efficiency (MSE), photocatalytic, antibacterial, and antibiofilm performances. Pure nanoparticles, having the highest saturation magnetization (Ms = 31.87 emu/g), exhibit the highest MSE, where 95.6% of nanoparticles were separated after 20 min of applying a magnetic field of 150 mT. The catalytic performance of the prepared samples is examined by the photodegradation of rhodamine B (RhB) dye exposed to direct sunlight radiation. Improved photocatalytic activity is exhibited by Co0.33Mg0.33Ni0.33Sm0.04Fe1.96O4 nanoparticles, labeled as Sm0.04, where the rate of the degradation reaction is enhanced by 4.1 times compared to pure nanoparticles. Rising the pH and reaction temperature improves the rate of the photodegradation reaction of RhB. The incorporation of 15 wt% reduced graphene oxide (rGO) with Sm0.04 enhanced the rate of the reaction by 1.7 and 2.4 times compared with pure Sm0.04 sample and rGO, respectively. The antibacterial and antibiofilm activities against Escherichia coli, Leclercia adecarboxylata, Staphylococcus aureus, and Enterococcus faecium are assessed by the minimum inhibitory concentration (MIC) and the minimum bactericidal concentration (MBC) broth microdilution, the agar well diffusion, the time-kill assays, the biofilm formation, and destruction assays. The bacteria used in these assessments are isolated from wastewater. The nanoparticles exhibit a bacteriostatic activity, with a better effect against the Gram-positive isolates. Co0.33Mg0.33Ni0.33SmxFe2O4 (x = 0.00) nanoparticles have the best effect. The effect is exerted after 2–3 h of incubation. Gram-positive biofilms are more sensitive to nanoparticles. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Iron compounds

来源：评论

学校读者我要写书评

暂无评论

Confidence-aware Contrastive Learning for Selective Classification 41

Confidence-aware Contrastive Learning for Selective Classifi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wu, Yu-Chang Lyu, Shen-Huan Shang, Haopu Wang, Xiangyu Qian, Chao National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Key Laboratory of Water Big Data Technology Ministry of Water Resources Hohai University China College of Computer Science and Software Engineering Hohai University China

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks and focus on modifying the architecture of classification layers to enable the model to estimate the confidence of its prediction. This work provides a generalization bound for selective classification, disclosing that optimizing feature layers helps improve the performance of selective classification. Inspired by this theory, we propose to explicitly improve the selective classification model at the feature level for the first time, leading to a novel Confidence-aware Contrastive Learning method for Selective Classification, CCL-SC, which similarizes the features of homogeneous instances and differentiates the features of heterogeneous instances, with the strength controlled by the model's confidence. The experimental results on typical datasets, i.e., CIFAR-10, CIFAR-100, CelebA, and ImageNet, show that CCL-SC achieves significantly lower selective risk than state-of-the-art methods, across almost all coverage degrees. Moreover, it can be combined with existing methods to bring further improvement. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Group Division Network for Referring Expression Comprehension

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 6170-6183页

作者： Ke, Jingcheng Wang, Jia Wong, Waikeung Toomey, Anne Wen, Jie Guangdong University of Technology School of Computer Science and Technology Guangzhou523083 China Guangdong Pharmaceutical University College of Medical Information Engineering Guangdong Guangzhou510006 China The Hong Kong Polytechnic University School of Fashion and Textiles Hong Kong Hong Kong Laboratory for Artificial Intelligence in Design Hong Kong Royal College of Art School of Design LondonSW7 2EU United Kingdom Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China

Referring expression comprehension (REC) aims at locating the target object described by an expression. We observe that most of the graph-based REC methods only focus on establishing relations between all objects in an image and the given expression during the graph construction while ignoring the relationships between objects in the same category. As a result, these methods are sub-optimal in locating the target object described by the expression, particularly when the target object is surrounded by objects of similar categories. Meanwhile, during reasoning, numerous irrelevant objects are considered for expression, which will introduce significant harmful noise. To address these issues, this paper proposes a new graph-based group division network (GBGDN). Different from the existing works, our work partitions the constructed graphs into several sub-graphs based on the categories of objects and expressions. In each sub-graph, the common visual features of objects will be strengthened through a feature enhancement strategy. Subsequently, the enhanced sub-graphs and expressions undergo joint processing via a filtering-based reasoning module designed to reduce the influence of unrelated nodes in each sub-graph, facilitating more accurate reasoning and matching. Experimental results across various datasets, including RefCOCO /+/g, Flickr30K Entities, RefClef, and Ref-reasoning, showcase the superiority of our proposed method over existing approaches. Most importantly, our method does not need pre-training. © 1991-2012 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance 38

OneActor: Consistent Subject Generation via Cluster-Conditio...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Jiahao Yan, Caixia Lin, Haonan Zhang, Weizhan Wang, Mengmeng Gong, Tieliang Dai, Guang Sun, Hao School of Computer Science and Technology MOEKLINNS Xi'an Jiaotong University China State Key Laboratory of Communication Content Cognition China College of Computer Science and Technology Zhejiang University of Technology China SGIT AI Lab State Grid Corporation of China Switzerland China Telecom Artificial Intelligence Technology Co.Ltd. China

Text-to-image diffusion models benefit artists with high-quality image generation. Yet their stochastic nature hinders artists from creating consistent images of the same subject. Existing methods try to tackle this challenge and generate consistent content in various ways. However, they either depend on external restricted data or require expensive tuning of the diffusion model. For this issue, we propose a novel one-shot tuning paradigm, termed OneActor. It efficiently performs consistent subject generation solely driven by prompts via a learned semantic guidance to bypass the laborious backbone tuning. We lead the way to formalize the objective of consistent subject generation from a clustering perspective, and thus design a cluster-conditioned model. To mitigate the overfitting challenge shared by one-shot tuning pipelines, we augment the tuning with auxiliary samples and devise two inference strategies: semantic interpolation and cluster guidance. These techniques are later verified to significantly improve the generation quality. Comprehensive experiments show that our method outperforms a variety of baselines with satisfactory subject consistency, superior prompt conformity as well as high image quality. Our method is capable of multi-subject generation and compatible with popular diffusion extensions. Besides, we achieve a 4× faster tuning speed than tuning-based baselines and, if desired, avoid increasing the inference time. Furthermore, our method can be naturally utilized to pre-train a consistent subject generation network from scratch, which will implement this research task into more practical applications. Project page: https://***/OneActor-webpage/. © 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

Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

arXiv

引用

arXiv 2024年

作者： Gao, Songyang Ge, Qiming Shen, Wei Dou, Shihan Ye, Junjie Wang, Xiao Zheng, Rui Zou, Yicheng Chen, Zhi Yan, Hang Zhang, Qi Lin, Dahua Shanghai Artificial Intelligence Laboratory China School of Computer Science Fudan University China ByteDance Inc China

The success of AI assistants based on Language Models (LLMs) hinges on Reinforcement Learning from Human Feedback (RLHF) to comprehend and align with user intentions. However, traditional alignment algorithms, such as PPO, are hampered by complex annotation and training requirements. This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences. In this work, we introduce Linear Alignment, a novel algorithm that aligns language models with human preferences in one single inference step, eliminating the reliance on data annotation and model training. Linear alignment incorporates a new parameterization for policy optimization under divergence constraints, which enables the extraction of optimal policy in a closed-form manner and facilitates the direct estimation of the aligned response. Extensive experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment across diverse scenarios. Our code and dataset is published on https://***/Wizardcoast/Linear_***. © 2024, CC BY-NC-SA.

关键词： Human form models

来源：评论

学校读者我要写书评

暂无评论

Automatic Identification and Extraction of Assumptions on GitHub 29

Automatic Identification and Extraction of Assumptions on Gi...

引用

29th International DMS Conference on Visualization and Visual Languages, DMSVIVA 2023

作者： Yang, Chen Ma, Zinan Liang, Peng Liu, Xiaohua School of Artificial Intelligence Shenzhen Polytechnic Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science Wuhan University Wuhan China Hubei Luojia Laboratory Wuhan China

ISBN: (纸本)1891706578

In software development, due to the lack of knowledge or information, time pressure, complex context, and many other factors, various uncertainties emerge during the development process, leading to assumptions scattered in projects. Being unaware of certain assumptions can result in critical problems (e.g., system vulnerability and failures). The prerequisite of analyzing and understanding assumptions in software development is to identify and extract those assumptions with acceptable effort. In this paper, we proposed a tool (i.e., Assumption Miner) to automatically identify and extract assumptions on GitHub projects. To evaluate the applicability of Assumption Miner, we first presented an example of using the tool to mine assumptions from one large and popular deep learning framework project: the TensorFlow project on GitHub. We then conducted an evaluation of the tool. The results show that Assumption Miner can effectively identify and extract assumptions from the repositories on GitHub. Copyright © 2023 by KSI Research Inc. and Knowledge Systems Institute, USA.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

The Role of Depth, Width, and Tree Size in Expressiveness of Deep Forest 27

The Role of Depth, Width, and Tree Size in Expressiveness of...

引用

27th European Conference on artificial intelligence, ECAI 2024

作者： Lyu, Shen-Huan Wu, Jin-Hui Zheng, Qin-Cheng Ye, Baoliu Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University China College of Computer Science and Software Engineering Hohai University China National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9781643685489

Random forests are classical ensemble algorithms that construct multiple randomized decision trees and aggregate their predictions using naive averaging. Zhou and Feng [51] further propose a deep forest algorithm with multi-layer forests, which outperforms random forests in various tasks. The performance of deep forests is related to three hyperparameters in practice: depth, width, and tree size, but little has been known about its theoretical explanation. This work provides the first upper and lower bounds on the approximation complexity of deep forests concerning the three hyperparameters. Our results confirm the distinctive role of depth, which can exponentially enhance the expressiveness of deep forests compared with width and tree size. Experiments validate these theoretical findings. The detailed proof and code are available in the full version [31]. © 2024 The Authors.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual Transfer Learning for Low-Resource Speech Translation

Cross-Lingual Transfer Learning for Low-Resource Speech Tran...

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Sameer Khurana Nauman Dawalatabad Antoine Laurent Luis Vicente Pablo Gimeno Victoria Mingote James Glass Mitsubishi Electric Research Lab MIT Computer Science and Artificial Intelligence Laboratory LIUM University University of Zaragoza

ISBN: (数字)9798350374513

ISBN: (纸本)9798350374520

The paper presents a novel three-step transfer learning framework for enhancing cross-lingual transfer from high- to low-resource languages in the downstream application of Automatic Speech Translation. The approach integrates a semantic knowledge-distillation step into the existing two-step cross-lingual transfer learning framework XLS-R. This extra step aims to encode semantic knowledge in the multilingual speech encoder pre-trained via Self-Supervised Learning using unlabeled speech. Our proposed three-step cross-lingual transfer learning framework addresses the large cross-lingual transfer gap (TRFGap) observed in the XLS-R framework between high-resource and low-resource languages. We validate our proposal through extensive experiments and comparisons on the CoVoST-2 benchmark, showing significant improvements in translation performance, especially for low-resource languages, and a notable reduction in the TRFGap.

关键词： Transfer learning Semantics Self-supervised learning Benchmark testing Speech enhancement Signal processing Transformers

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：