检索结果-内蒙古大学图书馆

Ontology-driven hierarchical sparse coding for large-scale image classification

NEUROCOMPUTING 2019年 360卷 209-219页

作者： Zhang, Yan Qu, Yanyun Li, Cuihua Lei, Yunqi Fan, Jianping Xiamen Univ Fujian Key Lab Sensing & Comp Smart Cities Comp Sci Dept Xiamen Fujian Peoples R China Guizhou Normal Univ Sch Math Sci Guiyang Guizhou Peoples R China Univ North Carolina Charlotte Dept Comp Sci Charlotte NC USA

An ontology-driven hierarchical sparse representation is developed in this paper, which aims to support hierarchical learning for large scale image classification. Firstly, a two-layer ontology (semantic ontology and visual ontology) is built to organize large number of image classes hierarchically, where WordNet is used to construct semantic ontology and deep features extracted by Inception V3 are used to construct visual ontology (visual tree). Secondly, a novel algorithm based on Split Bregman Iteration is developed to learn hierarchical sparse representation, i.e., learning a shared dictionary and a set of class-specified dictionaries depending on the two-layer ontology. For multi-class image classification, a tree classifier is trained according to the two-layer ontology by using the hierarchical sparse representation. Thirdly, for a given test image, multiple paths are simultaneously evaluated to achieve optimal prediction of its class label. Our proposed approach has been evaluated over three benchmark datasets: ILSVRC2010, SUN397, and Caltech256, and the experimental results have demonstrated that our approach is better than the original joint dictionary learning method and can achieve better accuracy compared with other approaches which use handcrafted features. (C) 2019 Elsevier B.V. All rights reserved.

关键词： large-scale image classification Deep features Joint dictionary learning Split Bregman Iteration Hierarchical image classification

来源：评论

学校读者我要写书评

暂无评论

Learning multi-layer coarse-to-fine representations for large-scale image classification

引用

PATTERN RECOGNITION 2019年 91卷 175-189页

作者： Zhang, Ji Mei, Kuizhi Zheng, Yu Fan, Jianping Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China Xidian Univ Dept Elect Engn Xian 710071 Shaanxi Peoples R China Univ N Carolina Dept Comp Sci Charlotte NC 28223 USA

Recent studies on large-scale image classification mainly focus on categorizing images into 1000 object classes, and all these 1000 object classes are atomic and mutually exclusive in the semantic space. However, for a much larger set of image categories (such as the imageNet 10k dataset), some of them may come from the high-level (non-leaf) nodes of the concept ontology and could contain some other lower-level categories semantically. The research that classifies images into large numbers of image categories with such inter-category subsumption correlations has received rare attention. In this paper, a Visual-Semantic Tree is learned to organize 10k image categories hierarchically in a coarse-to-fine fashion, where both the inter-category visual similarities and inter-category semantic correlations are seamlessly integrated for tree construction. Additionally, a deep learning method is developed by integrating the Visual-Semantic Tree with deep CNNs to learn more discriminative tree classifiers for large-scale image classification. Our experimental results have demonstrated that the proposed Visual-Semantic Tree can effectively organize large-scale structural image categories and significantly boost the classification accuracy rates for both atomic image categories and high-level image categories. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Visual-semantic tree Inter-category correlation Multi-task learning Deep convolutional neural network large-scale image classification

来源：评论

学校读者我要写书评

暂无评论

Joint Dictionary Learning via Split Bregman Iteration for large-scale image classification 18th

Joint Dictionary Learning via Split Bregman Iteration for La...

引用

18th Pacific-Rim Conference on Multimedia (PCM)

作者： Qu, Yanyun Li, Hanqian Zhang, Yan Xiamen Univ Dept Comp Sci Xiamen Peoples R China

ISBN: (纸本)9783319773834;9783319773827

This paper aims at the hierarchical learning for large-scale image classification. Due to flexibility and capability, sparse representation is widely used in object recognition. The hierarchy is introduced to joint dictionary learning for large scale image classification. Because the joint dictionary learning model is non-quadratic, Split Bregman Iteration is used to solve the shared dictionary and the class-specified dictionary. Moreover, the deep feature generated by Inception-v3 is used for image representation. When a query image is input, two label prediction schemes are investigated: SVM and residual. The proposed approach is implemented on three benchmark datasets: ILSVRC2010, Oxford Flower image set and Caltech 256 and the experimental results demonstrate that our approach is better than the original joint dictionary learning method and achieves excellent accuracy compared with other handcrafted features.

关键词： large-scale image classification Deep features Joint dictionary learning Split Bregman Iteration Hierarchical classification

来源：评论

学校读者我要写书评

暂无评论

Joint Hierarchical Category Structure Learning and large-scale image classification

引用

IEEE TRANSACTIONS ON image PROCESSING 2017年第9期26卷 4331-4346页

作者： Qu, Yanyun Lin, Li Shen, Fumin Lu, Chang Wu, Yang Xie, Yuan Tao, Dacheng Xiamen Univ Dept Comp Sci Xiamen 361005 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Nara Inst Sci & Technol Inst Res Initiat Nara 6300192 Japan Chinese Acad Sci Control Inst Automat Res Ctr Precis Sensing Beijing 100190 Peoples R China Univ Technol Sydney Fac Engn & Informat Technol Ctr Artificial Intelligence Ultimo NSW 2007 Australia

We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and performance of large-scale multi-class classification. We propose a novel image classification method based on learning hierarchical inter-class structures. Specifically, we first design a fast algorithm to compute the similarity metric between categories, based on which a visual tree is constructed by hierarchical spectral clustering. Using the learned visual tree, a test sample label is efficiently predicted by searching for the best path over the entire tree. The proposed method is extensively evaluated on the ILSVRC2010 and Caltech 256 benchmark datasets. The experimental results show that our method obtains significantly better category hierarchies than other state-of-the-art visual treebased methods and, therefore, much more accurate classification.

关键词： Hierarchical learning large-scale image classification deep features visual tree N-best path

来源：评论

学校读者我要写书评

暂无评论

Hierarchical learning of multi-task sparse metrics for large-scale image classification

引用

Pattern Recognition 2017年 67卷 97-109页

作者： Yu Zheng Jianping Fan Ji Zhang Xinbo Gao Department of Electronic Engineering Xidian University Xi’an 710071 PR China Department of Computer Science University of North Carolina Charlotte NC 28223 USA Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an 710049 PR China

In this paper, a novel approach is developed to learn a tree of multi-task sparse metrics hierarchically over a visual tree to achieve a fast solution to large-scale image classification, where an enhanced visual tree is first learned to organize large numbers of image categories hierarchically in a coarse-to-fine fashion. Over the visual tree, a tree of multi-task sparse metrics is learned hierarchically by: (a) performing multi-task sparse metric learning over the sibling child nodes under the same parent node to explicitly separate their commonly-shared metric from their node-specific metrics; and (b) propagating the node-specific metric for the parent node to its sibling child nodes (at the next level of the visual tree), so that more discriminative metrics can be learned for controlling inter-level error propagation effectively. We have evaluated our hierarchical multi-task sparse metric learning algorithm over three different image sets and the experimental results demonstrated that our hierarchical multi-task sparse metric learning algorithm can obtain better performance than the state-of-the-art algorithms on large-scale image classification.

关键词： Hierarchical multi-task sparse metric learning Visual tree large-scale image classification

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning of Random Forests for large-scale image classification

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2016年第3期38卷 490-503页

作者： Ristin, Marko Guillaumin, Matthieu Gall, Juergen Van Gool, Luc Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland Univ Bonn Comp Vis Grp Bonn Germany

large image datasets such as imageNet or open-ended photo websites like Flickr are revealing new challenges to image classification that were not apparent in smaller, fixed sets. In particular, the efficient handling of dynamically growing datasets, where not only the amount of training data but also the number of classes increases over time, is a relatively unexplored problem. In this challenging setting, we study how two variants of Random Forests (RF) perform under four strategies to incorporate new classes while avoiding to retrain the RFs from scratch. The various strategies account for different trade-offs between classification accuracy and computational efficiency. In our extensive experiments, we show that both RF variants, one based on Nearest Class Mean classifiers and the other on SVMs, outperform conventional RFs and are well suited for incrementally learning new classes. In particular, we show that RFs initially trained with just 10 classes can be extended to 1,000 classes with an acceptable loss of accuracy compared to training from the full data and with great computational savings compared to retraining for each new batch of classes.

关键词： Incremental learning random forests large-scale image classification

来源：评论

学校读者我要写书评

暂无评论

Hierarchical learning of large-margin metrics for large-scale image classification

引用

NEUROCOMPUTING 2016年第0期208卷 46-58页

作者： Lei, Hao Mei, Kuizhi Xin, Jingmin Dong, Peixiang Fan, Jianping Chinese Acad Sci Xian Inst Opt & Precis Mech Xian 710119 Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Peoples R China Northwest Univ Sch Informat Sci & Technol Xian 710069 Peoples R China

large-scale image classification is a challenging task and has recently attracted active research interests. In this paper, a new algorithm is developed to achieve more effective implementation of large-scale image classification by hierarchical learning of large-margin metrics (HLMMs). A hierarchical visual tree is seamlessly integrated with metric learning to learn a set of node-specific/category-specific large margin metrics. First, a hierarchical visual tree is learned to characterize the inter-category visual correlations effectively and organize large numbers of image categories in a coarse-to-fine fashion. Second, a new algorithm is developed to support hierarchical learning of large-margin metrics by training nearest class mean (NCM) classifiers over our hierarchical visual tree. In addition, we also consider dimensionality reduction as a regularizer for high-dimensional data in our large-margin metric learning. Two top down approaches are developed for supporting hierarchical learning of large-margin metrics. We focus on learning more discriminative metrics for NCM node classifiers to identify the visually similar sub nodes (visually similar image categories) under the same parent node over our hierarchical visual tree. A mini-batch stochastic gradient descend method is used to optimize our HLMMs learning algorithm. The experimental results on imageNet large scale Visual Recognition Challenge 2010 dataset (ILSVRC2010) have demonstrated that our HLMMs learning algorithm is very promising for supporting large-scale image classification. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Visual tree Hierarchical learning large-margin metric learning Dimensionality reduction large-scale image classification

来源：评论

学校读者我要写书评

暂无评论

A Vector Quantization Based k-NN Approach for large-scale image classification 6

A Vector Quantization Based k-NN Approach for Large-Scale Im...

引用

6th International Conference on image Processing Theory, Tools and Applications (IPTA)

作者： Ozan, Ezgi Can Riabchenko, Ekaterina Kiranyaz, Serkan Gabbouj, Moncef Tampere Univ Technol Dept Signal Proc Tampere Finland Qatar Univ Coll Engn Dept Elect Engn Doha Qatar

ISBN: (纸本)9781467389105

The k-nearest-neighbour classifiers (k-NN) have been one of the simplest yet most effective approaches to instance based learning problem for image classification. However, with the growth of the size of image datasets and the number of dimensions of image descriptors, popularity of k-NNs has decreased due to their significant storage requirements and computational costs. In this paper we propose a vector quantization (VQ) based k-NN classifier, which has improved efficiency for both storage requirements and computational costs. We test the proposed method on publicly available large scale image datasets and show that the proposed method performs comparable to traditional k-NN with significantly better complexity and storage requirements.

关键词： k-NN Classifier Vector Quantization large-scale image classification

来源：评论

学校读者我要写书评

暂无评论

Evolutionary compact embedding for large-scale image classification

引用

INFORMATION SCIENCES 2015年 316卷 567-581页

作者： Liu, Li Shao, Ling Li, Xuelong Nanjing Univ Informat Sci & Technol Coll Elect & Informat Engn Nanjing 210044 Jiangsu Peoples R China Univ Sheffield Dept Elect & Elect Engn Sheffield S1 3JD S Yorkshire England Chinese Acad Sci XIOPM State Key Lab Transient Opt & Photon Xian 710119 Shannxi Peoples R China

Effective dimensionality reduction is a classical research area for many large-scale analysis tasks in computer vision. Several recent methods attempt to learn either graph embedding or binary hashing for fast and accurate applications. In this paper, we propose a novel framework to automatically learn the task-specific compact coding, called evolutionary compact embedding (ECE), which can be regarded as an optimization algorithm combining genetic programming (GP) and a boosting trick. As an evolutionary computation methodology, GP can solve problems inspired by natural evolution without any prior knowledge of the solutions. In our evolutionary architecture, each bit of ECE is iteratively computed using a binary classification function, which is generated through GP evolving by jointly minimizing its empirical risk with the AdaBoost strategy on a training set. We address this as greedy optimization leading to small Hamming distances for similar samples and large distances for dissimilar samples. We then evaluate ECE on four image datasets: USPS digital hand-writing, CMU PIE face, CIFAR-10 tiny image and SUN397 scene, showing the accurate and robust performance of our method for large-scale image classification. (C) 2014 Elsevier Inc. All rights reserved.

关键词： Dimensionality reduction large-scale image classification Evolutionary compact embedding Genetic programming AdaBoost

来源：评论

学校读者我要写书评

暂无评论

Cost-sensitive learning of hierarchical tree classifiers for large-scale image classification and novel category detection

引用

Pattern Recognition 2015年第5期48卷 1673-1687页

作者： Jianping Fan Ji Zhang Kuizhi Mei Jinye Peng Ling Gao School of Information Science and Technology Northwest University Xi'an PR China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an 710049 PR China

In this paper, a cost-sensitive learning algorithm is developed to train hierarchical tree classifiers for large-scale image classification application (i.e., categorizing large-scale images into thousands of object classes). A visual tree is first constructed for organizing large numbers of object classes hierarchically and identifying inter-related learning tasks automatically. For the fine-grained object classes at the sibling leaf nodes, they share significant common visual properties but still contain subtle visual differences, thus a multi-task structural learning algorithm is developed to train their inter-related classifiers jointly to enhance their discrimination power. For the coarse-grained categories (i.e., groups of visually similar object classes) at the sibling non-leaf nodes, a hierarchical learning algorithm is developed to leverage tree structure (by adding two inter-level constraints) to train their inter-related classifiers jointly and control inter-level error propagation effectively. To achieve more robust detection of large numbers of object classes, a visual forest is learned by combining multiple visual trees (for different configurations) and their hierarchical tree classifiers. By penalizing various types of misclassification errors differently, a cost-sensitive learning approach is further developed to detect the appearances of new object classes accurately, and an incremental learning algorithm is developed to achieve more effective training of the discriminative classifiers for new object classes. Our experimental results have demonstrated that our cost-sensitive hierarchical learning algorithm can achieve very competitive results on both classification accuracy and computational efficiency as compared with other state-of-the-art techniques.

关键词： large-scale image classification Novel category detection Visual tree Visual forest Hierarchical tree classifiers Cost-sensitive hierarchical learning Incremental learning

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：