检索结果-内蒙古大学图书馆

Semi-supervised dictionary learning with label propagation for image classification

Computational Visual Media 2017年第1期3卷 83-94页

作者： Lin Chen Meng Yang College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina School of Data and Computer Science Sun Yat-sen UniversityGuangzhouChina Key Laboratory of Machine Intelligence and Advanced Computing(Sun Yat-sen University) Ministry of EducationChina

Sparse coding and supervised dictionary learning have rapidly developed in recent years,and achieved impressive performance in image classification. However, there is usually a limited number of labeled training samples and a huge amount of unlabeled data in practical image classification,which degrades the discrimination of the learned dictionary. How to effectively utilize unlabeled training data and explore the information hidden in unlabeled data has drawn much attention of researchers. In this paper, we propose a novel discriminative semisupervised dictionary learning method using label propagation(SSD-LP). Specifically, we utilize a label propagation algorithm based on class-specific reconstruction errors to accurately estimate the identities of unlabeled training samples, and develop an algorithm for optimizing the discriminative dictionary and discriminative coding vectors *** experiments on face recognition, digit recognition, and texture classification demonstrate the effectiveness of the proposed method.

关键词： semi-supervised learning dictionary learning label propagation image classification

来源：评论

学校读者我要写书评

暂无评论

Learning to Mitigate Extreme Distribution Bias for Few-Shot Object Detection

Learning to Mitigate Extreme Distribution Bias for Few-Shot ...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Wu, Faming Hu, Yanxu Wang, Jinpeng Ma, Andy J. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Few-shot object detection is an important but challenging task where only a few instances of novel categories are available. The widely used approach is to pretrain a detector on base classes with abundant samples and then fine-tune it for novel classes. Due to the extreme data imbalance between base and novel classes, the detection performance of novel classes degrades with the distribution bias. To overcome this limitation, we propose a distribution calibration strategy and a class discrimination regularization method for better few-shot detection. Based on theoretical analysis on decision margins of base and novel classes, the decision area of novel classes is enlarged to balance the prediction probability. On the other hand, to increase the separability of inter-class distributions, the similarity between class-specific representations is minimized. Extensive experiments on PASCAL VOC and MS COCO datasets verify the effectiveness and generalization ability of our method to improve few-shot object detection. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Finding Emotional Focus for Emotion Recognition at Sentence Level

引用

电子学报(英文版) 2013年第1期22卷 99-103页

作者： QUAN Changqin REN Fuji Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei 230009 China Faculty of Engineering The University of Tokushima Tokushima Japan

Emotion recognition at sentence level is one of the fundamental problems of textual emotion un- derstanding. Based on the observation that sentence emo- tional focus can be expressed by some clauses in this sen- tence, this paper proposes to find the emotional focus for sentence emotion recognition. For the sake of breaking through the problems brought about by depending on emo- tion lexicons, we first recognize word emotions in a sen- tence based on Maximum entropy model. And then homo- geneous Markov model is built for clause emotion recogni- tion; After that, a strategy based on emotion selection is proposed for a sentence with multiple clauses, and genetic algorithm is used for clause selection by textual feature weighting. The experimental results show that, comparing with the baseline, there are 9.1% and 3.6% improvement respectively for two different evaluations. It is demon- strated that finding emotional focus by clause selection is able to improve the performance of sentence emotion recognition significantly.

关键词：情感识别句子层面聚焦马尔可夫模型最大熵模型特征加权遗传算法

来源：评论

学校读者我要写书评

暂无评论

Region-Interactive Proposal Network and Class-Interactive Feature Learning for Few-Shot Object Detection

Region-Interactive Proposal Network and Class-Interactive Fe...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Hu, Yanxu Wu, Faming Wang, Jinpeng Ma, Andy J. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Few-shot object detection is a promising approach to solving the problem of detecting novel objects with only limited annotated data for training. Most existing methods are developed based on the progress in few-shot classification, which pay little attention to improving the localization module and modelling class interrelation. To address these issues, this paper proposes two novel modules, namely Region-interactive Proposal Network (Ri-PN) and Class-interactive Feature Learning (Ci-FL), for better localization and classification performance, respectively. In the Ri-PN, regions of novel classes are interacted with base classes via graph convolution instead of background due to the stronger relevance between base and novel classes together with the guidance of supervised regions loss. On the other hand, the Ci-FL refines class-specific features in prototypical learning by attentive graph convolutional network. Experimental results on PASCAL VOC and MS COCO datasets verify the superiority of our method for few-shot object detection. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

IMPROVING WEAKLY SUPERVISED OBJECT LOCALIZATION BY UNCERTAINTY ESTIMATION OF PSEUDO SUPERVISION

IMPROVING WEAKLY SUPERVISED OBJECT LOCALIZATION BY UNCERTAIN...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Chen, Xi Ma, Andy J. Guo, Nanxi Chen, Jiajia School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781665438643

Pseudo bounding box supervision is a promising approach for weakly supervised object localization (WSOL) with only image-level labels. However, the generated pseudo bounding boxes may be inaccurate or even completely non-overlapped with the objects of interest. In this paper, we propose to estimate the uncertainty of pseudo bounding boxes such that the negative impact caused by inaccurate estimation of pseudo supervision could be alleviated for better WSOL. The refined bounding boxes and corresponding variance uncertainties are learned by training a neural network regressor to penalize the erroneous estimations. To the best of our knowledge, this is the first work to incorporate uncertainty information of pseudo bounding boxes for WSOL. Experimental results show that our method not only outperforms previous state-of-the-art methods in CUB-200-2011 and ILSVRC datasets but also gives more precise bounding box prediction when the IoU threshold is higher. © 2021 IEEE

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Ensemble transductive learning for skin lesion segmentation 1

引用

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

作者： Cui, Zhiying Wu, Longshi Wang, Ruixuan Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Automated segmentation of skin lesions from dermoscopy images is helpful for the diagnosis and treatment of skin cancers. However, due to small annotated training set and the large visual difference in skins and lesions between subjects, the generalization performance of segmentation models are often limited. Inspired by the transductive learning for image classification, we propose a transductive segmentation approach for skin lesion segmentation, by choosing some of the pixels in test images to participate the training of any segmentation model together with the training set. In this way, visual features in the test images can be effectively learned during model training. Comprehensive evaluations with different model structures and transductive learning strategies showed that the proposed transductive segmentation approach always improve the performance of the corresponding state-of-the-art segmentation models in skin lesion segmentation. © Springer Nature Switzerland AG 2019.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Point of interest recommendation with social and geographical influence 4

Point of interest recommendation with social and geographica...

引用

4th IEEE International Conference on Big Data, Big Data 2016

作者： Zhang, Da-Chuan Li, Mei Wang, Chang-Dong School of Data and Computer Science Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781467390040

Point of interest (POI) recommendation, a service which can help people discover useful and interesting locations has emerged rapidly with the development of location-based social networks (LBSNs), like Foursquare, Gowalla and Wechat. The large number of check-in histories make it possible to mine the preference of each user and then to provide accurate personalized POI recommendation. In real-world applications, apart from check-in data, there are some other useful information available for making better POI recommendation, such as social relationship among users and geographical influence. In this paper, a new POI recommendation method called Social and Geographical Fusing Model (SGFM) is designed. The basic idea is summarized as follows. Firstly, the users' check-in records and social influence are integrated in a combinative model. Then the global user impact factors generated by the PageRank algorithm are used to improve the combinative model. Secondly, a geographical influence measurement is used to capture the users' physical check-in characters. Finally, the enhanced combinative model and geographical influence are combined together to form a new framework. Extensive experiments have been conducted on a famous dataset, namely Gowalla. The comparison results confirm that the proposed framework outperforms state-of-the-art POI recommendation methods significantly. © 2016 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Development of a novel autonomous lower extremity exoskeleton robot for walking assistance

引用

Frontiers of Information Technology & Electronic Engineering 2019年第3期20卷 318-329页

作者： Yong HE Nan LI Chao WANG Lin-qing XIA Xu YONG Xin-yu WU Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Department of Mechanical Engineering and Intelligent Systems the University of Electro-Communications

Today, exoskeletons are widely applied to provide walking assistance for patients with lower limb motor incapacity. Most existing exoskeletons are under-actuated, resulting in a series of problems, e.g., interference and unnatural gait during walking. In this study, we propose a novel intelligent autonomous lower extremity exoskeleton(Auto-LEE), aiming at improving the user experience of wearable walking aids and extending their application *** traditional exoskeletons, Auto-LEE has 10 degrees of freedom, and all the joints are actuated independently by direct current motors, which allows the robot to maintain balance in aiding walking without extra *** new exoskeleton is designed and developed with a modular structure concept and multi-modal human-robot interfaces are considered in the control system. To validate the ability of self-balancing bipedal walking, three general algorithms for generating walking patterns are researched, and a preliminary experiment is implemented.

关键词： Lower-limb Exoskeleton Self-balancing Bipedal walking Modular design

来源：评论

学校读者我要写书评

暂无评论

Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data 38

Revealing Distribution Discrepancy by Sampling Transfer in U...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Zhilin Cao, Longbing Fan, Xuhui Zheng, Wei-Shi School of Computing Macquarie University Australia School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

There are increasing cases where the class labels of test samples are unavailable, creating a significant need and challenge in measuring the discrepancy between training and test distributions. This distribution discrepancy complicates the assessment of whether the hypothesis selected by an algorithm on training samples remains applicable to test samples. We present a novel approach called Importance Divergence (I-Div) to address the challenge of test label unavailability, enabling distribution discrepancy evaluation using only training samples. I-Div transfers the sampling patterns from the test distribution to the training distribution by estimating density and likelihood ratios. Specifically, the density ratio, informed by the selected hypothesis, is obtained by minimizing the Kullback-Leibler divergence between the actual and estimated input distributions. Simultaneously, the likelihood ratio is adjusted according to the density ratio by reducing the generalization error of the distribution discrepancy as transformed through the two ratios. Experimentally, I-Div accurately quantifies the distribution discrepancy, as evidenced by a wide range of complex data scenarios and tasks. © 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

94LVI Algorithms of OIpU(One-Iteration-per-Update) Type Handling Time-Dependent QP(Quadratic Programming) with Two Constraints 41

94LVI Algorithms of OIpU(One-Iteration-per-Update) Type Hand...

引用

第41届中国控制会议

作者： Yunong Zhang Zhiwen Yuan School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Research Institute of Sun Yat-sen University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper presents three relatively effective numerical algorithms,i.e.,94 LVI algorithms of OIpU(one-iteration-perupdate) type,to handle time-dependent QP(quadratic programming) problems subject to two constraints respectively(i.e.,equality and inequality constraints,equality and bound constraints,or inequality and bound constraints).Specifically,two "bridges" play essential parts of the methods(i.e.,the first "bridge" makes a QP problem convert to an LVI [linear variational inequality],and the second "bridge" makes the LVI convert to a PLPE [piecewise-linear projection equation]).On the basis of the standard94 LVI algorithm,the methods only update once through the solution of the previous sampling time ***,we conduct a number of experiments to substantiate the three algorithms respectively,which use exponential functions,log functions,and trigonometric functions in corresponding coefficients of the experimental examples.

关键词： Quadratic programming Time-dependent Numerical algorithms Linear variational inequalities(LVI)

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：