Deep sparse representation-based mid-level visual elements discovery in fine-grained classification

doi:10.1007/s00500-018-3468-3

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 深度强化学习

	Deep sparse representation-based mid-level visual elements discovery in fine-grained classification
	Lv, Le; Zhao, Dongbin; Shao, Kun
发表期刊	SOFT COMPUTING
ISSN	1432-7643
	2019-09-01
卷号	23 期号:18 页码:8711-8722
通讯作者	Zhao, Dongbin(dongbin.zhao@ia.ac.cn)
摘要	In this paper, we propose a new mid-level visual elements discovery method and apply it to the fine-grained classification. We present the duality between image patches and features extracted by the convolutional winner-take-all autoencoder (CONV-WTA-AE). The sparsity constraints used by CONV-WTA-AE make a group of objects sharing the same feature components. Hence, the image patches could be clustered by their sharing feature components and the feature components can be clustered by their co-occurrence in the image patches. We propose formulating the mid-level visual elements mining as a bipartite graph partitioning problem. The spectral partitioning algorithm is employed to co-cluster image patches and feature components. The CONV-WTA-AE is an unsupervised feature learning method. Hence, it avoids using expensive annotations. Our experiments demonstrate that the spectral partitioning method is very efficient but only the confident instances in a cluster are well discriminated. The similarity metric used by this algorithm is not accurate enough. Hence, we propose training a group of linear support vector machine (SVM) to refine the clustering results. These SVMs will be trained on the initial confident instances and provide a better discriminative similarity. Then we can re-assign instances to each clusters. To avoid overfitting, this process is iterated on many data subsets. We conduct a series of experiments on the MNIST dataset to verify our algorithm. The experimental results show that our method can discover meaningful image patch clusters. In the fine-grained classification task, visual elements are input into an ensemble of convolutional neural networks. The experiments on the CompCars dataset illustrate that our method can achieve the state-of-the-art performance.
关键词	Mid-level visual elements discovery Fine-grained classification Winner-take-all autoencoder Bipartite graph spectral partitioning
DOI	10.1007/s00500-018-3468-3
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[61273136] ; National Natural Science Foundation of China (NSFC)[61573353] ; National Natural Science Foundation of China (NSFC)[61533017] ; National Natural Science Foundation of China (NSFC)[61273136] ; National Natural Science Foundation of China (NSFC)[61573353] ; National Natural Science Foundation of China (NSFC)[61533017]
项目资助者	National Natural Science Foundation of China (NSFC)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications
WOS记录号	WOS:000478897000031
出版者	SPRINGER
七大方向——子方向分类	强化与进化学习
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/27554
专题	多模态人工智能系统全国重点实验室_深度强化学习
通讯作者	Zhao, Dongbin
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Lv, Le,Zhao, Dongbin,Shao, Kun. Deep sparse representation-based mid-level visual elements discovery in fine-grained classification[J]. SOFT COMPUTING,2019,23(18):8711-8722.
APA	Lv, Le,Zhao, Dongbin,&Shao, Kun.(2019).Deep sparse representation-based mid-level visual elements discovery in fine-grained classification.SOFT COMPUTING,23(18),8711-8722.
MLA	Lv, Le,et al."Deep sparse representation-based mid-level visual elements discovery in fine-grained classification".SOFT COMPUTING 23.18(2019):8711-8722.