检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Chang, Dongliang Pang, Kaiyue Zheng, Yixiao Ma, Zhanyu Song, Yi-Zhe Guo, Jun The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China SketchX CVSSP University of Surrey London United Kingdom

Whether what you see in Figure 1 is a "flamingo" or a "bird", is the question we ask in this paper. While fine-grained visual classification (FGVC) strives to arrive at the former, for the majority of us non-experts just "bird" would probably suffice. The real question is therefore – how can we tailor for different fine-grained definitions under divergent levels of expertise. For that, we re-envisage the traditional setting of FGVC, from single-label classification, to that of top-down traversal of a pre-defined coarse-to-fine label hierarchy – so that our answer becomes "bird" = "Phoenicopteriformes" = "Phoenicopteridae" = "flamingo". To approach this new problem, we first conduct a comprehensive human study where we confirm that most participants prefer multi-granularity labels, regardless whether they consider themselves experts. We then discover the key intuition that: coarse-level label prediction exacerbates fine-grained feature learning, yet fine-level feature betters the learning of coarse-level classifier. This discovery enables us to design a very simple albeit surprisingly effective solution to our new problem, where we (i) leverage level-specific classification heads to disentangle coarse-level features with fine-grained ones, and (ii) allow finer-grained features to participate in coarser-grained label predictions, which in turn helps with better disentanglement. Experiments show that our method achieves superior performance in the new FGVC setting, and performs better than state-of-the-art on the traditional single-label FGVC problem as well. Thanks to its simplicity, our method can be easily implemented on top of any existing FGVC frameworks and is parameter-free. © 2020, CC BY.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Competing Ratio Loss for Multi-class image Classification 34

Competing Ratio Loss for Multi-class image Classification

引用

34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019

作者： Zhang, Ke Wang, Xinsheng Guo, Yurong Zhao, Zhenbing Ma, Zhanyu North China Electric Power University Department of Electronic and Communication Engineering Hebei China Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781728137230

Cross-entropy loss function (CEL) is widely used for training a multi-class classification deep convolutional neural network (DCNN). While CEL has been successfully implemented in image classification tasks, it only focuses on the posterior probability of correct class when the labels of training images are one-hot. It cannot be discriminated against the classes not belong to correct class (wrong classes) directly. Negative Log Likelihood Ratio Loss (NLLR) is proposed to better discriminate the correct class from competing wrong classes. But optimization of the loss function is normally presented as a minimization problem. In training DCNN, the value of NLLR is not constantly positive or negative, which affects the convergence of NLLR adversely. So, we propose competing ratio loss (CRL), which calculates the posterior probability ratio between the correct class and competing wrong classes to better widen the difference between the probability of the correct class and the probabilities of wrong classes, which also assures the value of CRL is constantly positive. Through massive experiments, we demonstrate the effectiveness and robustness of CRL on deep convolutional neural networks, our CRL outperforms CEL and NLLR on CIFAR-10/100 datasets. © 2019 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Action recognition Under Simulated Prosthetic Vision

Dynamic Action Recognition Under Simulated Prosthetic Vision

引用

International Conference on Networking and Network Applications (NaNA)

作者： Ying Zhao Dantong Xu Tie Wang Yanchun Ren Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing School of Information Engineering Inner Mongolia University of Science and Technology Baotou Inner Mongolia

ISBN: (数字)9781728189543

ISBN: (纸本)9781728189550

Purpose. To assess the recognition pattern of dynamic action by visual prosthesis' wearers. Methods. Twenty volunteers (classified by gender and experience) were recruited to carried out action recognition test in simulated prosthetic vision. Twenty-three common dynamic actions video clips usually see in daily life were selected and formed the experimental action set which was divided into three parts including combined actions, simple actions and difficult actions in turn. The action animations made by 3D Studio Max were recorded by Banicam to convert to MP4 video format and processed to phosphene video clips by MATLAB in different resolutions (16 × 16, 24 × 24, 32 × 32, 48 × 48, 64 × 64, 128 × 128). Result. Comparing the recognition results, male group and female group had no significant difference. 48 × 48 resolution was the considerable latent capacity which subjects had stable performance. After a period of study, the performance of prosthesis wearers could be improved significantly.

关键词： Three-dimensional displays Visual prosthesis Animation pattern recognition Matlab

来源：评论

学校读者我要写书评

暂无评论

Regional attention with architecture-rebuilt 3D network for RGB-D gesture recognition

arXiv

引用

arXiv 2021年

作者： Zhou, Benjia Li, Yunan Wan, Jun Macau University of Science and Technology China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China School of Computer Science and Technology Xidian Univeristy China Xi'an Key Laboratory of Big Data and Intelligent Vision China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Human gesture recognition has drawn much attention in the area of computer vision. However, the performance of gesture recognition is always influenced by some gesture-irrelevant factors like the background and the clothes of performers. Therefore, focusing on the regions of hand/arm is important to the gesture recognition. Meanwhile, a more adaptive architecture-searched network structure can also perform better than the block-fixed ones like ResNet since it increases the diversity of features in different stages of the network better. In this paper, we propose a regional attention with architecture-rebuilt 3D network (RAAR3DNet) for gesture recognition. We replace the fixed Inception modules with the automatically rebuilt structure through the network via Neural Architecture Search (NAS), owing to the different shape and representation ability of features in the early, middle, and late stage of the network. It enables the network to capture different levels of feature representations at different layers more adaptively. Meanwhile, we also design a stackable regional attention module called Dynamic-Static Attention (DSA), which derives a Gaussian guidance heatmap and dynamic motion map to highlight the hand/arm regions and the motion information in the spatial and temporal domains, respectively. Extensive experiments on two recent large-scale RGB-D gesture datasets validate the effectiveness of the proposed method and show it outperforms state-of-the-art methods. The codes of our method are available at: https://***/zhoubenjia/RAAR3DNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Multi-Weighted Complex Networks with Mixed Variable Delays and Uncertainties Via Impulsive Pinning Control

SSRN

引用

SSRN 2023年

作者： Fan, Hongguang Shi, Kaibo Wen, Hui Zhao, Yi College of Computer Chengdu University Chengdu610106 China Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu University Chengdu610106 China School of Electronic Information and Electrical Engineering Chengdu University Chengdu610106 China New Engineering Industry College Putian University Fujian Putian351100 China Engineering Research Center of Big Data Application in Private Health Medicine Fujian Province University Fujian Putian351100 China College of Mathematical and Statistical Shenzhen University Shenzhen518060 China

In this paper, we examine the synchronization problem in nonlinearly-coupled multi-weighted complex networks that contain uncertainties and varying delays. The complexities of these networks arise from the presence of both internal time-varying delays and multiple coupling time-varying delays. To address this challenge, we employ impulsive pinning control schemes and incorporate the impulsive pinning control ratio in the construction of the Lyapunov function, which allows us to determine the optimal number of pinned nodes at each pulse instant. Our analysis, based on stability theory, provides synchronization criteria that are strongly dependent on the multi-weights and time delays present in the network. Finally, we present numerical simulations of a delayed complex network to demonstrate the validity and efficacy of our derived theoretical results. © 2023, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Scaling Solar Photocatalytic Hydrogen Production in China: Integrated Geospatial-Meteorological Analysis

SSRN

引用

SSRN 2024年

作者： Li, Yinan Li, Lanyu Yuan, Hongkuan He, Keji Chen, Hong Xie, Jianping Wang, Biao Wang, Xiaonan School of Physical Science and Technology Southwest University Chongqing400715 China Department of Chemical and Biomolecular Engineering National University of Singapore Singapore117585 Singapore Department of Chemical Engineering Tsinghua University Beijing100084 China China Oilfield Services Limited Yanjiao065201 China Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing101408 China School of Resources and Environment Institute of Fundamental and Frontier Science University of Electronic Science and Technology of China Chengdu611731 China Chongqing key Laboratory of Micro Nano Structure Optoelectronics School of Physical Science and Technology Southwest University Chongqing400715 China

Solar photocatalytic hydrogen production is considered a promising technology owing to its sustainable nature, while facing the challenges of improving and maintaining photocatalytic efficiency under prolonged variable weather conditions. Herein, we screen out the MoTe2/ZrS2 system with a theoretical solar-to-hydrogen conversion efficiency of 10.37%. To improve the actual efficiency among all 97,711 grid cells in China, we propose an original meteorological data-driven machine learning model to optimize photocatalytic H2 production and results show that the annual average STH efficiency gives a mean of 3.16% within a range of 0.44% – 4.91% . Incorporating geospatial data, we determine that China's photocatalytic H2 potential is about 216.65 Mt/year, which has been improved by almost sixfold compared to that without optimization, and the country’s 2060 hydrogen demand can be met by using 11.08% of its total land area. Compared with photovoltaic electrolysis, a photocatalyst cost of 23 USD/m2cat/103hrs would make photocatalysis economically competitive. Last, considering hydrogen production fluctuations, we explore optimal operation of hydrogen storage and utilization facilities to fulfil downstream demands. © 2024, The Authors. All rights reserved.

关键词： Hydrogen production

来源：评论

学校读者我要写书评

暂无评论

Differentiable neural architecture learning for efficient neural network design

arXiv

引用

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageN

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

CASIA-Face-Africa: A large-scale African face image database

arXiv

引用

arXiv 2021年

作者： Muhammad, Jawad Wang, Yunlong Wang, Caiyong Zhang, Kunbo Sun, Zhenan The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China

Face recognition is a popular and well-studied area with wide applications in our society. However, racial bias had been proven to be inherent in most State Of The Art (SOTA) face recognition systems. Many investigative studies on face recognition algorithms have reported higher false positive rates of African subjects cohorts than the other cohorts. Lack of large-scale African face image databases in public domain is one of the main restrictions in studying the racial bias problem of face recognition. To this end, we collect a face image database namely CASIA-Face-Africa which contains 38,546 images of 1,183 African subjects. Multi-spectral cameras are utilized to capture the face images under various illumination settings. Demographic attributes and facial expressions of the subjects are also carefully recorded. For landmark detection, each face image in the database is manually labeled with 68 facial keypoints. A group of evaluation protocols are constructed according to different applications, tasks, partitions and scenarios. The performances of SOTA face recognition algorithms without retraining are reported as baselines. The proposed database along with its face landmark annotations, evaluation protocols and preliminary results form a good benchmark to study the essential aspects of face biometrics for African subjects, especially face image preprocessing, face feature analysis and matching, facial expression recognition, sex/age estimation, ethnic classification, face image generation, etc. The database can be downloaded from our website* Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Towards multimodal response generation with exemplar augmentation and curriculum optimization

arXiv

引用

arXiv 2020年

作者： Lei, Zeyang Li, Zekang Zhang, Jinchao Meng, Fandong Feng, Yang Yang, Yujiu Niu, Cheng Zhou, Jie Tsinghua University China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Pattern Recognition Center WeChat AI Tencent Inc China

Recently, variational auto-encoder (VAE) based approaches have made impressive progress on improving the diversity of generated responses. However, these methods usually suffer the cost of decreased relevance accompanied by diversity improvements (Zhang et al., 2018b). In this paper, we propose a novel multimodal1 response generation framework with exemplar augmentation and curriculum optimization to enhance relevance and diversity of generated responses. First, unlike existing VAE-based models that usually approximate a simple Gaussian posterior distribution, we present a Gaussian mixture posterior distribution (i.e, multimodal) to further boost response diversity, which helps capture complex semantics of responses. Then, to ensure that relevance does not decrease while diversity increases, we fully exploit similar examples (exemplars) retrieved from the training data into posterior distribution modeling to augment response relevance. Furthermore, to facilitate the convergence of Gaussian mixture prior and posterior distributions, we devise a curriculum optimization strategy to progressively train the model under multiple training criteria from easy to hard. Experimental results on widely used SwitchBoard and DailyDialog datasets demonstrate that our model achieves significant improvements compared to strong baselines in terms of diversity and relevance. Copyright © 2020, The Authors. All rights reserved.

关键词： Curricula

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：