检索结果-内蒙古大学图书馆

43rd International Conference on Computer-Aided Design, ICCAD 2024

作者： Liu, Shaoshan Zhu, Yuhao Yu, Bo Gaudiot, Jean-Luc Gao, Guang R. Shenzhen Institute of Artificial Intelligence and Robotics for Society China University of Rochester United States University of California Irvine United States University of Delaware United States

ISBN: (纸本)9798400710773

Commercial autonomous machines is a thriving sector, one that is likely the next ubiquitous computing platform, after Personal Computers (PC), cloud computing, and mobile computing. Nevertheless, a suitable computing substrate for autonomous machines is missing, and many companies are forced to develop ad hoc computing solutions that are neither principled nor extensible. By analyzing the demands of autonomous machine computing, this article proposes Dataflow Accelerator Architecture (DAA), a modern instantiation of the classic dataflow principle, that matches the characteristics of autonomous machine software. © 2024 Copyright is held by the owner/author(s).

关键词： Software architecture

来源：评论

学校读者我要写书评

暂无评论

Class Relevance Learning for Out-of-Distribution Detection

Class Relevance Learning for Out-of-Distribution Detection

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhou, Liguang Xiong, Butian Lam, Tin Lun Xu, Yangsheng School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen China

ISBN: (纸本)9798350368741

Image classification plays a pivotal role across diverse robotic applications, yet challenges persist when models are deployed in real-world scenarios. These models often fail to detect out-of-distribution (OOD) samples, classes not included in their training. This makes OOD detection a significant challenge for safe and effective real-world use. While existing techniques, like max logits, aim to leverage logits for OOD identification, they often disregard the intricate interclass relationships that underlie effective detection. This paper presents an innovative class relevance learning (CRL) method tailored for OOD detection. Our method establishes a comprehensive class relevance learning framework, strategically harnessing interclass relationships within the OOD pipeline. This framework significantly augments OOD detection capabilities. Extensive experimentation on diverse datasets, encompassing generic image classification datasets (Near OOD and Far OOD datasets), demonstrates the superiority of our method over state-of-the-art alternatives for OOD detection. The code is available on GitHub at: CRL. © 2025 IEEE.

关键词： class relevance learning out-of-distribution detection

来源：评论

学校读者我要写书评

暂无评论

Partial Channel Network: Compute Fewer, Perform Better

arXiv

引用

arXiv 2025年

作者： Huang, Haiduo Xia, Tian Zhao, Wenzhe Ren, Pengju Xi’an Jiaotong University Institute of Artificial Intelligence and Robotics China

Designing a module or mechanism that enables a network to maintain low parameters and FLOPs without sacrificing accuracy and throughput remains a challenge. To address this challenge and exploit the redundancy within feature map channels, we propose a new solution: partial channel mechanism (PCM). Specifically, through the split operation, the feature map channels are divided into different parts, with each part corresponding to different operations, such as convolution, attention, pooling, and identity mapping. Based on this assumption, we introduce a novel partial attention convolution (PATConv) that can efficiently combine convolution with visual attention. Our exploration indicates that the PATConv can completely replace both the regular convolution and the regular visual attention while reducing model parameters and FLOPs. Moreover, PATConv can derive three new types of blocks: Partial Channel-Attention block (PAT ch), Partial Spatial-Attention block (PAT sp) and Partial Self-Attention block (PAT sf). In addition, we propose a novel dynamic partial convolution (DPConv) that can adaptively learn the proportion of split channels in different layers to achieve better trade-offs. Building on PATConv and DPConv, we propose a new hybrid network family, named PartialNet, which achieves superior top-1 accuracy and inference speed compared to some SOTA models on ImageNet-1K classification and excels in both detection and segmentation on the COCO dataset. Our code is available at https://***/haiduo/PartialNet. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Attribute Recognition Using Hierarchical Transformers 27th

Pedestrian Attribute Recognition Using Hierarchical Transfor...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lohani, Lalit Thakare, Kamalakar Vijay Nayak, Kamakshya Prasad Dogra, Debi Prosad Choi, Heeseung Jung, Hyungjoo Kim, Ig-Jae Bhubaneswar752050 India Artificial Intelligence and Robotics Institute Korea Institute of Science and Technology Seoul02792 Korea Republic of Yonsei-KIST Convergence Research Institute Yonsei University Seoul03722 Korea Republic of

ISBN: (纸本)9783031784439

The goal of pedestrian attribute recognition (PAR) is to detect and classify a wide range of pedestrian attributes, such as gender, carrying objects, clothing styles, body postures, age groups, and more. It plays a vital role in computer vision, specifically in crucial applications such as behaviour analysis, public safety monitoring, and video surveillance. However, existing PAR approaches are unable to achieve substantial performance due to multiple factors. First, multiple appearances of the same attribute confuse the models. Second, adverse weather and lighting conditions restrict model generalization capability. To mitigate these challenges, this paper proposes a new evaluation baseline that uses Vision Transformer (ViT) blocks for hierarchical feature modelling. The approach categorizes attributes into different spatial granularity levels and employs diverse patch formations to extract discriminative features. Furthermore, we introduce an enhanced loss function for stable training in the re-formulated granularity scenario, where a novel attribute-aware granularity factor influences the loss. The proposed baseline has been extensively evaluated on the three popular PAR datasets, namely RAP, PA100K and PETA. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Pedestrian safety

来源：评论

学校读者我要写书评

暂无评论

KernelDNA: Dynamic Kernel Sharing via Decoupled Naive Adapters

arXiv

引用

arXiv 2025年

作者： Huang, Haiduo Zhang, Yadong Ren, Pengju Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical tradeoffs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) compromise inference speed through complex kernel interactions, or (3) struggle to jointly optimize dynamic attention and static kernels. We also observe that pre-trained Convolutional Neural Networks (CNNs) exhibit inter-layer redundancy akin to that in Large Language Models (LLMs). Specifically, dense convolutional layers can be efficiently replaced by derived "child" layers generated from a shared "parent" convolutional kernel through an adapter. To address these limitations and implement the weight-sharing mechanism, we propose a lightweight convolution kernel plug-in, named KernelDNA. It decouples kernel adaptation into input-dependent dynamic routing and pre-trained static modulation, ensuring both parameter efficiency and hardware-friendly inference. Unlike existing dynamic convolutions that expand parameters via multikernel ensembles, our method leverages cross-layer weight sharing and adapter-based modulation, enabling dynamic kernel specialization without altering the standard convolution structure. This design preserves the native computational efficiency of standard convolutions while enhancing representation power through input-adaptive kernel adjustments. Experiments on image classification and dense prediction tasks demonstrate that KernelDNA achieves state-ofthe-art accuracy-efficiency balance among dynamic convolution variants. Our codes are available at https://***/haiduo/KernelDNA 1 Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transforming Classification with Federated Learning on Blockchain: A Unique Model Integration Approach

Transforming Classification with Federated Learning on Block...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Hao, Zhihao Zhang, Bob Li, Haisheng School of Computer Science and Artificial Intelligence Beijing Technology and Business University Beijing China Dept. of Computer and Information Science Faculty of Science and Technology University of Macau Taipa China Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation University of Macau Taipa China

ISBN: (纸本)9798350368741

The need for robust machine learning models is particularly evident in the realm of biological pattern recognition. Traditional centralized methods often struggle, as they frequently depend on large datasets that are challenging to gather due to stringent data privacy regulations. To address these limitations while maintaining classification accuracy, we propose an innovative approach that unifies models with diverse architectures within a federated learning framework built on a blockchain network. This decentralized and trustworthy system fosters effective collaboration among various models. Furthermore, we have implemented a weight distribution mechanism designed to maximize the individual strengths of each model. By leveraging blockchains inherent transparency and auditability, this approach also ensures secure and traceable data exchanges among participants. Additionally, the adaptability of the framework allows it to be extended to other domains where privacy-preserving data sharing is critical. Our experimental results showcase that the proposed methodology significantly enhances performance in classification tasks compared to existing alternatives. © 2025 IEEE.

关键词： blockchain collaborative training Federated Learning heterogeneous models

来源：评论

学校读者我要写书评

暂无评论

REGNav: Room Expert Guided Image-Goal Navigation

arXiv

引用

arXiv 2025年

作者： Li, Pengna Wu, Kangyi Fu, Jingwen Zhou, Sanping Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Image-goal navigation aims to steer an agent towards the goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts visual features of goal and observation images, compares their similarity and predicts actions. However, if the agent is in a different room from the goal image, it’s extremely challenging to identify their similarity and infer the likely goal location, which may result in the agent wandering around. Intuitively, when humans carry out this task, they may roughly compare the current observation with the goal image, having an approximate concept of whether they are in the same room before executing the actions. Inspired by this intuition, we try to imitate human behaviour and propose a Room Expert Guided Image-Goal Navigation model (REGNav) to equip the agent with the ability to analyze whether goal and observation images are taken in the same room. Specifically, we first pre-train a room expert with an unsupervised learning technique on the self-collected unlabelled room images. The expert can extract the hidden room style information of goal and observation images and predict their relationship about whether they belong to the same room. In addition, two different fusion approaches are explored to efficiently guide the agent navigation with the room relation knowledge. Extensive experiments show that our REGNav surpasses prior state-of-the-art works on three popular benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

ICPR 2024 Competition on Multilingual Claim-Span Identification 27th

ICPR 2024 Competition on Multilingual Claim-Span Identifica...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Poddar, Soham Paul, Biswajit Basu, Moumita Ghosh, Saptarshi Indian Institute of Technology Kharagpur Kharagpur721302 India Centre for Artificial Intelligence and Robotics DRDO Bangalore560093 India NSHM Institute of Computing and Analytics NSHM Knowledge Campus Kolkata700053 India

ISBN: (纸本)9783031801389

A lot of claims are made in social media posts, which may contain misinformation or fake news. Hence, it is crucial to identify claims as a first step towards claim verification. Given the huge number of social media posts, the task of identifying claims needs to be automated. This competition deals with the task of ‘Claim Span Identification’ in which, given a text, parts/spans that correspond to claims are to be identified. This task is more challenging than the traditional binary classification of text into claim or not-claim, and requires state-of-the-art methods in Pattern Recognition, Natural Language Processing and Machine Learning. For this competition, we used a newly developed dataset called HECSI containing about 8K posts in English and about 8K posts in Hindi with claim-spans marked by human annotators. This paper gives an overview of the competition, and the solutions developed by the participating teams. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Claim detection Claim-span identification English Hindi social media

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Tracking Control of a Cushion Robot with Safe Autonomous Motion Considering Human-Machine Interaction Environment

引用

Journal of Dynamic Systems, Measurement and Control 2025年第4期147卷 041003页

作者： Sun, Ping Shan, Rui Chang, Hongbin Wang, Shuoyu School of Artificial Intelligence Shenyang University of Technology Shenyang110870 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110169 China Department of Intelligent Mechanical Systems Engineering Kochi University of Technology Kochi7828502 Japan

This study proposes a data-driven safety controller with velocity constraints for a cushion robot. We constructed a mathematical description of the human-machine interaction environment by decomposing the generalized input force and coefficient matrix in the dynamic model. We established a new equivalent data model, which considered various human-machine interaction environments using a pseudo-Jacobian matrix. A stochastic configuration network (SCN) estimation method for variations in the human-machine interaction environment was proposed, with hidden layer nodes added at random. We designed a safe autonomous navigation path and proposed a data-driven control method that limited the actual velocity while stabilizing the tracking error system. In addition, the desired motion velocity of the robot was designed. This approach has the advantage of ensuring safety at a specified velocity. We also demonstrated and validated the effectiveness of the proposed data-driven algorithm using simulation-based comparative analysis and an experimental study. Copyright © 2024 by ASME.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

PromptTA: Prompt-driven Text Adapter for Source-free Domain Generalization

PromptTA: Prompt-driven Text Adapter for Source-free Domain ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haoran Zhang Shuanghao Bai Wanqi Zhou Jingwen Fu Badong Chen Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Source-free domain generalization (SFDG) tackles the challenge of adapting models to unseen target domains without access to source domain data. To deal with this challenging task, recent advances in SFDG have primarily focused on leveraging the text modality of vision-language models such as CLIP. These methods involve developing a transferable linear classifier based on diverse style features extracted from the text and learned prompts or deriving domain-unified text representations from domain banks. However, both style features and domain banks have limitations in capturing comprehensive domain knowledge. In this work, we propose Prompt-Driven Text Adapter (PromptTA) method, which is designed to better capture the distribution of style features and employ resampling to ensure thorough coverage of domain knowledge. To further leverage this rich domain information, we introduce a text adapter that learns from these style features for efficient domain information storage. Extensive experiments conducted on four benchmark datasets demonstrate that PromptTA achieves state-of-the-art performance. The code is available at https://***/zhanghr2001/PromptTA.

关键词： Adaptation models Codes Benchmark testing Signal processing Feature extraction Data models Acoustics Speech processing

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：