A novel CNN model for fine-grained classification with large spatial variants

doi:10.1088/1742-6596/1544/1/012138

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	A novel CNN model for fine-grained classification with large spatial variants
	Wang,Junpeng1,2 ; Lu,Yanfeng 1
发表期刊	Journal of Physics: Conference Series
ISSN	1742-6588
	2020-05-01
卷号	1544 期号:1
摘要	Abstract Convolutional Neural Networks (CNN) have achieved great performance in many visual tasks. However, CNN models are sensitive to samples with large spatial variants, especially severe in fine-grained classification task. In this paper, we propose a novel CNN model called ST-BCNN to solve these problems. ST-BCNN contains two functional CNN modules: Spatial Transform Network (STN) and Bilinear CNN(BCNN). Firstly, STN module is used to select key region in input samples and get it spatially modified. Since the adoption of STN will cause an information loss phenomenon called boundary loss, we design a brand-new IOU loss method to solve it. We make a theoretical analysis of the IOU loss method. Secondly, to discover discriminative features for fine-grained classification task, BCNN module is applied. BCNN interacts CNN features from different channels to produce more discriminative bilinear features than fully connected features of CNN. ST-BCNN works by reducing irrelevant spatial states and producing fine-grained features. We evaluate our model on 3 public fine-grained classification datasets with large spatial variants: CUB200-2011, Fish100 and UAV43. Experiments show that the IOU loss method can reduce boundary loss and make STN module output spatial transformed image appropriately. Our proposed ST-BCNN model outperforms other advanced CNN models on all three datasets.
DOI	10.1088/1742-6596/1544/1/012138
语种	英语
WOS记录号	IOP:1742-6588-1544-1-012138
出版者	IOP Publishing
七大方向——子方向分类	机器学习
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/39831
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
作者单位	1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wang,Junpeng,Lu,Yanfeng. A novel CNN model for fine-grained classification with large spatial variants[J]. Journal of Physics: Conference Series,2020,1544(1).
APA	Wang,Junpeng,&Lu,Yanfeng.(2020).A novel CNN model for fine-grained classification with large spatial variants.Journal of Physics: Conference Series,1544(1).
MLA	Wang,Junpeng,et al."A novel CNN model for fine-grained classification with large spatial variants".Journal of Physics: Conference Series 1544.1(2020).