arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1403.3829cs.CV
收藏

用于大规模图像搜索的几何VLAD

Geometric VLAD for Large Scale Image Search

Stanford University(斯坦福大学);eBay Research Labs, eBay Inc.(eBay公司 eBay研究实验室)

Zixuan Wang, Wei Di, Anurag Bhardwaj, Vignesh Jagadeesh, Robinson Piramuthu

摘要:

我们提出了一种新的紧凑的图像描述符大规模图像搜索。我们提出的描述符-几何VLAD(gVLAD)是一个扩展的VLAD(矢量局部聚集描述符),将弱几何信息到VLAD框架。所提出的几何线索是作为一个隶属函数的关键点的角度,其中包含明显的和翔实的信息,但往往被丢弃。还提出了一个原则性的技术,学习隶属度函数的聚类角度。此外,为了解决实时数据集上的迭代码本训练的开销,概述了一种新的码本自适应策略。最后,我们证明了建议的gVLAD为基础的检索框架,我们实现了超过15%的改进,在现有的基准mAP的功效。

英文摘要:

We present a novel compact image descriptor for large scale image search. Our proposed descriptor - Geometric VLAD (gVLAD) is an extension of VLAD (Vector of Locally Aggregated Descriptors) that incorporates weak geometry information into the VLAD framework. The proposed geometry cues are derived as a membership function over keypoint angles which contain evident and informative information but yet often discarded. A principled technique for learning the membership function by clustering angles is also presented. Further, to address the overhead of iterative codebook training over real-time datasets, a novel codebook adaptation strategy is outlined. Finally, we demonstrate the efficacy of proposed gVLAD based retrieval framework where we achieve more than 15% improvement in mAP over existing benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑