QQ客服 官方微博 反馈留言

	The application of two-level attention models in deep convolutional neural network for fine-grained image classification
	Xiao, Tianjun ; Xu, Yichong ; Yang, Kuiyuan ; Zhang, Jiaxing ; Peng, Yuxin ; Zhang, Zheng
	2015
英文摘要	Fine-grained classification is challenging because categories can only be discriminated by subtle and local differences. Variances in the pose, scale or rotation usually make the problem more difficult. Most fine-grained classification systems follow the pipeline of finding foreground object or object parts (where) to extract discriminative features (what). In this paper, we propose to apply visual attention to finegrained classification task using deep neural network. Our pipeline integrates three types of attention: the bottom-up attention that propose candidate patches, the object-level top-down attention that selects relevant patches to a certain object, and the part-level top-down attention that localizes discriminative parts. We combine these attentions to train domain-specific deep nets, then use it to improve both the what and where aspects. Importantly, we avoid using expensive annotations like bounding box or part information from end-to-end. The weak supervision constraint makes our work easier to generalize. We have verified the effectiveness of the method on the subsets of ILSVRC2012 dataset and CUB200 2011 dataset. Our pipeline delivered significant improvements and achieved the best accuracy under the weakest supervision condition. The performance is competitive against other methods that rely on additional annotations. ? 2015 IEEE.; EI; 842-850; 07-12-June-2015
语种	英语
出处	IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
DOI标识	10.1109/CVPR.2015.7298685
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/436560]
专题	计算机科学技术研究所
推荐引用方式 GB/T 7714	Xiao, Tianjun,Xu, Yichong,Yang, Kuiyuan,et al. The application of two-level attention models in deep convolutional neural network for fine-grained image classification. 2015-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。