检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Yong Sun, Yufei Cui, Zhen Shan, Shiguang Yang, Jian Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology

Face recognition (FR) has made extraordinary progress owing to the advancement of deep convolutional neural networks. However, demographic bias among different racial cohorts still challenges the practical face recognition system. The race factor has been proven to be a dilemma for fair FR (FFR) as the subject-related specific attributes induce the classification bias whilst carrying some useful cues for FR. To mitigate racial bias and meantime preserve robust FR, we abstract face identityrelated representation as a signal denoising problem and propose a progressive cross transformer (PCT) method for fair face recognition. Originating from the signal decomposition theory, we attempt to decouple face representation into i) identity-related components and ii) noisy/identity-unrelated components induced by race. As an extension of signal subspace decomposition, we formulate face decoupling as a generalized functional expression model to cross-predict face identity and race information. The face expression model is further concretized by designing dual cross-transformers to distill identity-related components and suppress racial noises. In order to refine face representation, we take a progressive face decoupling way to learn identity/racespecific transformations, so that identity-unrelated components induced by race could be better disentangled. We evaluate the proposed PCT on the public fair face recognition benchmarks (BFW, RFW) and verify that PCT is capable of mitigating bias in face recognition while achieving state-of-the-art FR performance. Besides, visualization results also show that the attention maps in PCT can well reveal the race-related/biased facial regions. © 2021, CC BY-NC-SA.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient Random Subspace Decision Forests with A Simple Probability Dimensionality Setting Scheme

SSRN

引用

SSRN 2022年

作者： Wang, Quan Wang, Fei Li, Zhongheng Jiang, Peilin Ren, Fuji Nie, Feiping Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing100094 China School of Software Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China Northwestern Polytechnical University Shaanxi Xi’an710072 China

The random subspace concept is widely used in decision forests. However, there is not a reasonable approach to specify the appropriate number of randomly selected features. Previous random subspace decision forests simply specify the random subspace dimensionality d s to a preset function value such as [log 2 d ] or [√ d ] where d is the number of the total feature dimensions. Actually, this preset value may be a relatively poor choice for high dimensional data sets. In this paper, a novel framework named Efficient Random Subspace decision forest (ERS) is proposed which pays attention to how to set the random subspace dimensionality for each decision tree of decision forests. Specifically, a simple discrete uniform distribution is employed to set with probability the number of randomly selected features for each tree in random subspace decision forests. The proposed Half Range Discrete Uniform distribution-based Varied Dimensionality setting (HRDUVD) method removes the hesitation of how to preset an appropriate d s for different data sets but also results in good enough classification performance along with relatively short running time. Plenty of experiments on public benchmark data sets have demonstrated the effectiveness and the efficiency of the proposed ERS. © 2022, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Towards High-accuracy and Low-latency Spiking Neural Networks with Two-Stage Optimization

arXiv

引用

arXiv 2022年

作者： Wang, Ziming Zhang, Yuhao Lian, Shuang Cui, Xiaoxin Yan, Rui Tang, Huajin College of Computer Science and Technology Zhejiang University Hangzhou310027 China Research Center for Intelligent Computing Hardware Zhejiang Lab Hangzhou311100 China School of Integrated Circuits Peking University Beijing100871 China College of Computer Science Zhejiang University of Technology Hangzhou310014 China State Key Laboratory of Brain-Machine Intelligence Zhejiang University Hangzhou310027 China

Spiking neural networks (SNNs) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs and efficient inference of SNNs. However, the accuracy loss is usually non-negligible, especially under few time steps, which restricts the applications of SNN on latencysensitive edge devices greatly. In this paper, we first identify that such performance degradation stems from the misrepresentation of the negative or overflow residual membrane potential in SNNs. Inspired by this, we decompose the conversion error into three parts: quantization error, clipping error, and residual membrane potential representation error. With such insights, we propose a two-stage conversion algorithm to minimize those errors respectively. Besides, We show each stage achieves significant performance gains in a complementary manner. By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the stateof- the-art performance in terms of accuracy, latency and energy preservation. Furthermore, our method is evaluated using a more challenging object detection task, revealing notable gains in regression performance under ultra-low latency when compared to existing spike-based detection algorithms. Codes are available at https://***/Windere/snn-cvt-dual-phase. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A New Anomaly Detector of Flare Pilot Based on Siamese Network

A New Anomaly Detector of Flare Pilot Based on Siamese Netwo...

引用

Chinese Automation Congress (CAC)

作者： Xiaotian Xie Ke Gu Junfei Qiao Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China Beijing Artificial Intelligence Institute Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

The flare pilot is the key to ensure that the flare system is ignited at any time. At present, domestic and foreign companies mainly use thermocouples, flame ionization detectors and other sensors to detect the working condition of the flare pilot. These electronic components have the hysteretic and vulnerable problems due to extreme heat, thermal shock and vibration, which may well further lead to the failure to ignite the flare gas with flare pilot in time and cause production accidents. In view of the above problems, this paper proposes an anomaly detector of flare pilot based on deep learning technology. First of all, we made an anomaly detection database for flare pilot, which was shot in a domestic petrochemical company. Then, we designed a specific siamese network based on the triplet loss function for learning the similarity between the samples, in order to apply to the curing scene of the flare pilot. Finally, it is determined whether the flare pilot is abnormal according to the similarity between the input picture and the positive and negative samples. Experimental results demonstrate that the proposed method can be effectively used for the anomaly detection of flare pilot.

关键词： Databases Anomaly detection Petrochemicals Feature extraction Employee welfare Detectors Combustion

来源：评论

学校读者我要写书评

暂无评论

Exploring the Spatial Correlation of Shadowing in RF-based Device-Free Localization by Block Sparse Bayesian Learning

Exploring the Spatial Correlation of Shadowing in RF-based D...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Jiaju Tan Xin Zhao Xuemei Guo Guoli Wang School of Mathematics and Computational Science Wuyi University Jiangmen China Tianjin Key Laboratory of Intelligent Robotic (tjKLIR) Institute of Robotics and Automatic Information System (IRAIS) Nankai University Tianjin China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education School of Data and Computer Science Sun Yat-sen University Guangzhou China

ISBN: (纸本)9781665405362

Device-Free Localization (DFL) realized by the Radio Frequency (RF) signal sensing, is an emerging technology to obtain the target’s position without needing the target carrying any electronic devices or tags. Due to its through-wall detectability and privacy protection, the RF-based DFL is becoming a promising research topic in the Location-based Services (LBS) applications based on Internet of Things (IoT). Among the RF-based DFL approaches, Radio Tomographic Imaging (RTI) is a low-cost and novel computational imaging method to reconstruct the target-induced shadowing effect in the RF monitored area and then estimate the target’s position. However, the multipath interference in the RF sensing network often induces the reconstruction degradation in the RTI system and leads to the position misestimation in DFL applications. Addressing this problem, considering that the target’s shadowing may occupy a small spatial range and then express some spatial structure, this aricle focuses on the spatial correlation of the target’s shadowing. Then an RTI reconstruction methods based on the Block Sparse Bayesian Learning is proposed to explore the spatial correlation in the sparse target’s shadowing. Moreover, the actual localization experiments are conducted to validate the spatial correlation in shadowing is an important property to improve the RTI reconstruction performance and DFL accuracy.

关键词： Performance evaluation Location awareness Radio frequency Correlation Robot sensing systems Bayes methods Sensors

来源：评论

学校读者我要写书评

暂无评论

Face super-resolution via discriminative-attributes 1

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Dong, Ning Li, Xiaoguang Li, Jiafeng Zhuo, Li Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China Faculty of Information Technology Beijing University of Technology Beijing100124 China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

The limited resolution of cameras and the wide field of the video surveillance systems lead to low quality captured facial images and difficult to identify. Face super-resolution methods are proposed to enhance the resolution of facial images. However, it remains a challenging issue to restore discriminative features to identify a specific person in surveillance videos. An algorithm that helps face super-resolution and recognition with the aid of discriminative-attributes is proposed in this paper. We introduce discriminative-attributes for face recognition to recover discriminative features in the reconstructed facial images. Attributes with more discriminative power are selected to input the network together with the low-resolution face image. The experimental results of the LFW-a benchmark test show that our method achieves promising results in both subjective visual quality and face recognition accuracy. © Springer Nature Switzerland AG 2019.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

AQPDCITY dataset: Picture-based PM monitoring in the urban area of big cities

arXiv

引用

arXiv 2020年

作者： Zhang, Yonghui Gu, Ke Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Key Laboratory of Computational Intelligence and Intelligent System China Beijing Artificial Intelligence Institute China Faculty of Information Technology Beijing University of Technology China

Since Particulate Matters (PMs) are closely related to people’s living and health, it has become one of the most important indicator of air quality monitoring around the world. But the existing sensor-based methods for PM monitoring have remarkable disadvantages, such as low-density monitoring stations and high-requirement monitoring conditions. It is highly desired to devise a method that can obtain the PM concentration at any location for the following air quality control in time. The prior works indicate that the PM concentration can be monitored by using ubiquitous photos. To further investigate such issue, we gathered 1,500 photos in big cities to establish a new AQPDCITY dataset. Experiments conducted to check nine state-of-the-art methods on this dataset show that the performance of those above methods perform poorly in the AQPDCITY dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Yang, Jian Qi, Guo-Jun Lin, Chia-Wen Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100080 China Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China School of Communication and Information Engineering Shanghai University Shanghai200444 China School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China Research Center for Industries of the Future the School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan

Lightweight image super-resolution aims to reconstruct high-resolution images from low-resolution images using low computational costs. However, existing methods result in the loss of middle-layer features due to activation functions. To minimize the impact of intermediate feature loss on reconstruction quality, we propose a Feature Interaction Weighted Hybrid Network (FIWHN), which comprises a series of Wide-residual Distillation Interaction Block (WDIB) as the backbone. Every third WDIB forms a Feature Shuffle Weighted Group (FSWG) by applying mutual information shuffle and fusion. Moreover, to mitigate the negative effects of intermediate feature loss, we introduce Wide Residual Weighting units within WDIB. These units effectively fuse features of varying levels of detail through a Wide-residual Distillation Connection (WRDC) and a Self-Calibrating Fusion (SCF). To compensate for global feature deficiencies, we incorporate a Transformer and explore a novel architecture to combine CNN and Transformer. We show that our FIWHN achieves a favorable balance between performance and efficiency through extensive experiments on low-level and high-level tasks. Codes will be available at https://***/IVIPLab/FIWHN. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Sequence Matching with Discriminative Binary Features for Robust and Fast Light-Rail Localization at High Frame Rate

Sequence Matching with Discriminative Binary Features for Ro...

引用

IEEE International Conference on Big Data

作者： Tingxian Wang Kebin Jia Meng Yao Faculty of Information Technology Beijing University of Technology Beijing China Beijing Laboratory of Advanced Information Networks Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China

ISBN: (数字)9781728162515

ISBN: (纸本)9781728162522

As an essential part of the advanced driving assistant system, visual localization technology has drawn much attention. To solve the interference caused by the high similarity of scenes at a high frame rate, this paper proposes a localization method based on global-local features and keyframe retrieval. In this method, the semantic features of the scene extracted by the fused semantic segmentation model are used to guide the detection of the key regions with discriminative information. By using the screening strategy based on pixel position cues and unsupervised learning algorithm, the binary feature descriptor with strong discrimination power is extracted, which can improve the matching accuracy and reduce the computational complexity. Secondly, combining the keyframes obtained by calculating scene discriminative score with a sequence matching algorithm can promote localization performance. The experiments conducted on the Nordland dataset and the challenging Hong Kong light rail dataset. The experiment results show that our method has higher computing efficiency and locating accuracy than the state-of-the-art ConvNet featurebased localization method named SeqCNNSLAM under the condition of drastic changes in appearance. Moreover, compared with SeqSLAM which is based on global features, the precision of our approach has significant improvement while meeting real-time requirements.

关键词： Location awareness Visualization Semantics Light rail systems Feature extraction Real-time systems Data mining

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multiobjective Optimal Control with Knowledge-Decision for Wastewater Treatment Process

Dynamic Multiobjective Optimal Control with Knowledge-Decisi...

引用

International Conference on Informative and Cybernetics for Computational Social systems (ICCSS)

作者： Linlin Zhang Honggui Han Junfei Qiao Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education Beijing Artificial Intelligence Institute and Beijing Laboratory For Urban Mass Transit Beijing University of Technology Beijing China

ISBN: (数字)9781728162461

ISBN: (纸本)9781665419352

Optimal control system plays an important role in the stability and safety of wastewater treatment process (WWTP). However, because of the dynamic complex mechanism of WWTP, it is challenging to decide the suitable set-points of manipulated variables for improving optimal control performance in the dynamic complex environment. Therefore, a dynamic multiobjective optimal control with knowledge-decision (DMOC-KD) is proposed in this paper. First, a dynamic multiobjective optimal control scheme is presented to adapt the dynamic complex environment of WWTP. Second, an adaptive multiobjective particle swarm optimization (AMOPSO), based on distributed knowledge, is presented to determine the suitable optimal set-points of WWTP. Third, a fuzzy neural network (FNN) control method is designed to track the obtained optimal set-points for keeping effluent equality and reducing energy consumption. Finally, this DMOC-KD is compared with other optimal control strategies on benchmark simulation model 1 (BSM1). The results show that this DMOC-KD is superior than most compared strategies.

关键词： Fuzzy control Optimal control Process control Fuzzy neural networks Wastewater treatment Particle swarm optimization Manipulator dynamics

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：