Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics

doi:10.1007/s11633-019-1177-8

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics
	Ao-Xue Li; Ke-Xin Zhang; Li-Wei Wang
刊名	International Journal of Automation and Computing
	2019
卷号	16 期号:5 页码:563-574
关键词	Fine-grained image classification zero-shot learning deep feature learning domain adaptation semantic graph.
ISSN号	1476-8186
DOI	10.1007/s11633-019-1177-8
英文摘要	Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zero-shot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot fine-grained classification.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42358]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	The Key Laboratory of Machine Perception (MOE), School of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
推荐引用方式 GB/T 7714	Ao-Xue Li,Ke-Xin Zhang,Li-Wei Wang. Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics[J]. International Journal of Automation and Computing,2019,16(5):563-574.
APA	Ao-Xue Li,Ke-Xin Zhang,&Li-Wei Wang.(2019).Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics.International Journal of Automation and Computing,16(5),563-574.
MLA	Ao-Xue Li,et al."Zero-shot Fine-grained Classification by Deep Feature Learning with Semantics".International Journal of Automation and Computing 16.5(2019):563-574.