QQ客服 官方微博 反馈留言

	HIERARCHICAL MULTI-VLAD FOR IMAGE RETRIEVAL
	Wang, Yitong ; Duan, Ling-Yu ; Lin, Jie ; Wang, Zhe ; Huang, Tiejun
	2015
关键词	Image Retrieval Hierarchical Quantization Multi-VLAD VISUAL-SEARCH FISHER CODES FEATURES
英文摘要	Constructing discriminative feature descriptors is crucial towards effective image retrieval. The state-of-the-art powerful global descriptor for this purpose is Vector of Locally Aggregated Descriptors (VLAD). Given a set of local features (say, SIFT) extracted from an image, the VLAD is generated by quantizing local features with a small visual vocabulary (64 to 512 centroids), aggregating the residual statistics of quantized features for each centroid and concatenating the aggregated residual vectors from each centroid. One can increase the search accuracy by increasing the size of vocabulary (from hundreds to hundreds of thousands), which, however, it leads to heavy computation cost with flat quantization. In this paper, we propose a hierarchical multi-VLAD to seek the tradeoff between descriptor discriminability and computation complexity. We build up a tree-structured hierarchical quantization (TSHQ) to accelerate the VLAD computation with a large vocabulary. As quantization error may propagate from root to leaf node (centroid) with TSHQ, we introduce multi-VLAD, which constructing a VLAD descriptor for each level of the vocabulary tree, so as to compensate for the quantization error at that level. Extensive evaluation over benchmark datasets has shown that the proposed approach outperforms state-of-the-art in terms of retrieval accuracy, fast extraction, as well as light memory cost.; EI; CPCI-S(ISTP); wangyitong@pku.edu.cn; lingyu@pku.edu.cn; lin-j@i2r.a-star.edu.sg; zwang@pku.edu.cn; tjhuang@pku.edu.cn; 4629-4633; 2015-December
语种	英语
出处	2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
DOI标识	10.1109/ICIP.2015.7351684
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/436416]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Wang, Yitong,Duan, Ling-Yu,Lin, Jie,et al. HIERARCHICAL MULTI-VLAD FOR IMAGE RETRIEVAL. 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。