检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xilin He Jingyu Hu Qinliang Lin Cheng Luo Weicheng Xie Siyang Song Muhammad Haris Khan Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University and Shenzhen Institute of Artificial Intelligence and Robotics for Society and Guangdong Provincial Key Laboratory of Intelligent Information Processing University of Exeter Mohamed bin Zayed University of Artificial Intelligence

ISBN: (纸本)9798331314385

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models' biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at https://***/C0notSilly/AdvFrequency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Tang, Canhui Zhou, Sanping Li, Yizhe Dong, Yonghao Wang, Le The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi 710049 China

With the wide application of knowledge distillation between an ImageNet pre-trained teacher model and a learnable student model, industrial anomaly detection has witnessed a significant achievement in the past few years. The success of knowledge distillation mainly relies on how to keep the feature discrepancy between the teacher and student model, in which it assumes that: (1) the teacher model can jointly represent two different distributions for the normal and abnormal patterns, while (2) the student model can only reconstruct the normal distribution. However, it still remains a challenging issue to maintain these ideal assumptions in practice. In this paper, we propose a simple yet effective two-stage industrial anomaly detection framework, termed as AAND, which sequentially performs Anomaly Amplification and Normality Distillation to obtain robust feature discrepancy. In the first anomaly amplification stage, we propose a novel Residual Anomaly Amplification (RAA) module to advance the pre-trained teacher encoder. With the exposure of synthetic anomalies, it amplifies anomalies via residual generation while maintaining the integrity of pre-trained model. It mainly comprises a Matching-guided Residual Gate and an Attribute-scaling Residual Generator, which can determine the residuals’ proportion and characteristic, respectively. In the second normality distillation stage, we further employ a reverse distillation paradigm to train a student decoder, in which a novel Hard Knowledge Distillation (HKD) loss is built to better facilitate the reconstruction of normal patterns. Comprehensive experiments on the MvTecAD, VisA, and MvTec3D-RGB datasets show that our method achieves state-of-the-art performance. Our code will be available at https://***/Hui-design/AAND. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Healthcare Monitoring Companion: The Social Robot

Healthcare Monitoring Companion: The Social Robot

引用

artificial intelligence For Internet of Things (AIIoT), International Conference on

作者： Rahul Goraksha Arunkumar Bongale Sameer Sayyad Satish Kumar Department of Robotics and Automation Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India Department of Robotics and Automation Symbiosis Centre for Applied Artificial Intelligence Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

There is a rising scarcity of healthcare professionals to meet the demand of taking care of aged people. Social robots are becoming more and more popular because of the benefits they provide; during the pandemic, in particular, several of their primary applications are advantageous. The purpose of this work is to build the prototype of social robots and carry out the integration of those robots into healthcare monitoring using Thing Speak and Raspberry Pi. This prototype of social robots with Thing Speak and Raspberry Pi hosts an array of sensors (for measuring a multitude of data from the body of humans) like heartbeat sensor, Dallas temperature sensor, Radio-Frequency Identification (RFID), ultrasonic sensor, and Infrared (IR) sensor along with other components like motor controlling module and DC motor. The data from these sensors are transmitted to the cloud platform Thing Speak, offering remote monitoring and data analysis capabilities and the Raspberry Pi acts as the central processing element in our design, which additionally helps in triggering corresponding alerts regarding the patient status. Finally, we experimentally validate our design using 2 cases and then we present the assessment of the patient alerting feature.

关键词： Temperature sensors Temperature measurement Ultrasonic variables measurement Social robots Prototypes Medical services Sensors

来源：评论

学校读者我要写书评

暂无评论

OpenSatMap: a fine-grained high-resolution satellite dataset for large-scale map construction 24

OpenSatMap: a fine-grained high-resolution satellite dataset...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hongbo Zhao Lue Fan Yuntao Chen Haochen Wang Yuran Yang Xiaojuan Jin Yixin Zhang Gaofeng Meng Zhaoxiang Zhang Institute of Automation Chinese Academy of Sciences (CASIA) and University of Chinese Academy of Sciences (UCAS) Centre for Artificial Intelligence and Robotics HKISI CAS Tencent Maps Tencent and Beijing University of Posts and Telecommunications Institute of Automation Chinese Academy of Sciences (CASIA) Tencent Maps Tencent Institute of Automation Chinese Academy of Sciences (CASIA) and Centre for Artificial Intelligence and Robotics HKISI CAS and University of Chinese Academy of Sciences (UCAS)

ISBN: (纸本)9798331314385

In this paper, we propose OpenSatMap, a fine-grained, high-resolution satellite dataset for large-scale map construction. Map construction is one of the foundations of the transportation industry, such as navigation and autonomous driving. Extracting road structures from satellite images is an efficient way to construct large-scale maps. However, existing satellite datasets provide only coarse semantic-level labels with a relatively low resolution (up to level 19), impeding the advancement of this field. In contrast, the proposed OpenSatMap (1) has fine-grained instance-level annotations; (2) consists of high-resolution images (level 20); (3) is currently the largest one of its kind; (4) collects data with high diversity. Moreover, OpenSatMap covers and aligns with the popular nuScenes dataset and Argoverse 2 dataset to potentially advance autonomous driving technologies. By publishing and main taining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CaKDP: Category-Aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection

CaKDP: Category-Aware Knowledge Distillation and Pruning Fra...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haonan Zhang Longjun Liu Yuqi Huang Zhao Yang Xinyu Lei Bihan Wen National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Nanyang Technological University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Knowledge distillation (KD) possesses immense potential to accelerate the deep neural networks (DNNs) for LiDAR-based 3D detection. However, in most of prevailing approaches, the suboptimal teacher models and insufficient student architecture investigations limit the performance gains. To address these issues, we propose a simple yet effective Category-aware Knowledge Distillation and Pruning (CaKDP) framework for compressing 3D detectors. Firstly, CaKDP transfers the knowledge of two-stage detector to one-stage student one, mitigating the impact of inadequate teacher models. To bridge the gap between the heterogeneous detectors, we investigate their differences, and then introduce the student-motivated category-aware KD to align the category prediction between distillation pairs. Secondly, we propose a category-aware pruning scheme to obtain the customizable architecture of compact student model. The method calculates the category prediction gap before and after removing each filter to evaluate the importance of filters, and retains the important filters. Finally, to further improve the student performance, a modified IOU-aware refinement module with negligible computations is leveraged to remove the redundant false positive predictions. Experiments demonstrate that CaKDP achieves the compact detector with high performance. For example, on WOD, CaKDP accelerates CenterPoint by half while boosting L2 mAPH by 1.61%. The code is available at https://***/zhnxjtu/CaKDP.

关键词： Knowledge engineering Computer vision Three-dimensional displays Computational modeling Detectors Computer architecture Object detection

来源：评论

学校读者我要写书评

暂无评论

CLIPping Imbalances: A Novel Evaluation Baseline and PEARL Dataset for Pedestrian Attribute Recognition

CLIPping Imbalances: A Novel Evaluation Baseline and PEARL D...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

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

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Pedestrian Attribute Recognition (PAR) serves as a fun-damental task in computer vision and is crucial for upgradign security systems. It helps in precisely identifying and characterizing various attributes of pedestrians. However, current PAR datasets have certain issues in representing a wide range of attributes correctly, which makes the ex-isting PAR methods less effective in real-world scenarios. Addressing this limitation, this paper introduces PEARL, a comprehensive dataset comprising of diverse pedestrian images annotated with 146 attributes. These samples have been sourced from surveillance videos across twelve coun-tries. This paper also formulates an image-based PAR using language-image fusion strategy and utilizes CLIP as a new evaluation baseline. Specifically, we leverage textual infor-mation by transforming sets of attributes into meaningful sentences. Addressing the inherent data imbalance in PAR, we provide three types of prompt settings to optimize the training of the CLIP model. Our evaluation encompasses a thorough assessment of the proposed baseline model across various datasets, including PEARL dataset as well as estab-lished PAR benchmarks such as PA100K, RAP, and PETA.

关键词： Training Computer vision Pedestrians Computational modeling Surveillance Contrastive learning Benchmark testing Data models Security Videos

来源：评论

学校读者我要写书评

暂无评论

Improved Capon Estimator for High-Resolution DOA Estimation and Its Statistical Analysis

Improved Capon Estimator for High-Resolution DOA Estimation ...

引用

作者： Zuo, Weiliang Xin, Jingmin Liu, Changnong Zheng, Nanning Sano, Akira National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'An Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi'an710049 China Data Center China Construction Bank Beijing100033 China Keio University Department of System Design Engineering Yokohama223-8522 Japan

Despite some efforts and attempts have been made to improve the direction-of-arrival (DOA) estimation performance of the standard Capon beamformer (SCB) in array processing, rigorous statistical performance analyses of these modified Capon estimators are still lacking. This paper studies an improved Capon estimator (ICE) for estimating the DOAs of multiple uncorrelated narrowband signals, where the higher-order inverse (sample) array covariance matrix is used in the Capon-like cost function. By establishing the relationship between this nonparametric estimator and the parametric and classic subspace-based MUSIC (multiple signal classification), it is clarified that as long as the power order of the inverse covariance matrix is increased to reduce the influence of signal subspace components in the ICE, the estimation performance of the ICE becomes equivalent to that of the MUSIC regardless of the signal-to-noise ratio (SNR). Furthermore the statistical performance of the ICE is analyzed, and the large-sample mean-squared-error (MSE) expression of the estimated DOA is derived. Finally the effectiveness and the theoretical analysis of the ICE are substantiated through numerical examples, where the Cramer-Rao lower bound (CRB) is used to evaluate the validity of the derived asymptotic MSE expression. © 2014 Chinese Association of Automation.

关键词： Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

Variance reduced EXTRA and DIGing and their optimal acceleration for strongly convex decentralized optimization

引用

The Journal of Machine Learning Research 2022年第1期23卷 10057-10097页

作者： Huan Li Zhouchen Lin Yongchun Fang Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin China Key Laboratory of Machine Perception School of Artificial Intelligence Peking University Beijing China

We study stochastic decentralized optimization for the problem of training machine learning models with large-scale distributed data. We extend the widely used EXTRA and DIGing methods with variance reduction (VR), and propose two methods: VR-EXTRA and VR-DIGing. The proposed VR-EXTRA requires the time of O((κs+n) log 1/ε) stochastic gradient evaluations and O((κb + κc) log 1/ε) communication rounds to reach precision ε, which are the best complexities among the non-accelerated gradient-type methods, where κs and κb are the stochastic condition number and batch condition number for strongly convex and smooth problems, respectively, κc is the condition number of the communication network, and n is the sample size on each distributed node. The proposed VR-DIGing has a little higher communication cost of O((κb + κ2b) log 1/ε). Our stochastic gradient computation complexities are the same as the ones of single-machine VR methods, such as SAG, SAGA, and SVRG, and our communication complexities keep the same as those of EXTRA and DIGing, respectively. To further speed up the convergence, we also propose the accelerated VR-EXTRA and VR-DIGing with both the optimal O((√nκs+n) log 1/ε) stochastic gradient computation complexity and O(√κbκc log 1/ε) communication complexity. Our stochastic gradient computation complexity is also the same as the ones of single-machine accelerated VR methods, such as Katyusha, and our communication complexity keeps the same as those of accelerated full batch decentralized methods, such as MSDA. To the best of our knowledge, our accelerated methods are the first to achieve both the optimal stochastic gradient computation complexity and communication complexity in the class of gradient-type methods.

关键词： stochastic decentralized optimization EXTRA DIGing variance reduction acceleration

来源：评论

学校读者我要写书评

暂无评论

PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Fei Zhang, Xu-Yao Cheng, Zhen Liu, Cheng-Lin The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong999077 Hong Kong The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

Class-incremental learning (CIL) aims to recognize new classes incrementally while maintaining the discriminability of old classes. Most existing CIL methods are exemplar-based, i.e., storing a part of old data for retraining. Without relearning old data, those methods suffer from catastrophic forgetting. In this paper, we figure out two inherent problems in CIL, i.e., representation bias and classifier bias, that cause catastrophic forgetting of old knowledge. To address these two biases, we present a simple and novel dual bias reduction framework that employs self-supervised transformation (SST) in input space and prototype augmentation (protoAug) in deep feature space. On the one hand, SST alleviates the representation bias by learning generic and diverse representations that can transfer across different tasks. On the other hand, protoAug overcomes the classifier bias by explicitly or implicitly augmenting prototypes of old classes in the deep feature space, which poses tighter constraints to maintain previously learned decision boundaries. We further propose hardness-aware prototype augmentation and multi-view ensemble strategies, leading to significant improvements. The proposed framework can be easily integrated with pre-trained models. Without storing any samples of old classes, our method can perform comparably with state-of-the-art exemplar-based approaches which store plenty of old data. We hope to draw the attention of researchers back to non-exemplar CIL by rethinking the necessity of storing old samples in CIL. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Text Grouping Adapter: Adapting Pre-Trained Text Detector for Layout Analysis

Text Grouping Adapter: Adapting Pre-Trained Text Detector fo...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tianci Bi Xiaoyi Zhang Zhizheng Zhang Wenxuan Xie Cuiling Lan Yan Lu Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Microsoft Research Asia

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Significant progress has been made in scene text detection models since the rise of deep learning, but scene text layout analysis, which aims to group detected text instances as paragraphs, has not kept pace. Previous works either treated text detection and grouping using separate models, or train a model from scratch while using a unified one. All of them have not yet made full use of the already well-trained text detectors and easily obtainable detection datasets. In this paper, we present Text Grouping Adapter (TGA), a module that can enable the utilization of various pretrained text detectors to learn layout analysis, allowing us to adopt a well-trained text detector right off the shelf or just fine-tune it efficiently. Designed to be compatible with various text detector architectures, TGA takes detected text regions and image features as universal inputs to as-semble text instance features. To capture broader contextual information for layout analysis, we propose to predict text group masks from text instance features by one-to-many assignment. Our comprehensive experiments demonstrate that, even with frozen pretrained models, incorporating our TGA into various pretrained text detectors and text spotters can achieve superior layout analysis performance, simultaneously inheriting generalized text detection ability from pretraining. In the case of full parameter fine-tuning, we can further improve layout analysis performance.

关键词： Deep learning Analytical models Adaptation models Computer vision Layout Text detection Detectors

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：