Efficient region-aware large graph construction towards scalable multi-label propagation
Efficient region-aware large graph construction towards scalable multi-label propagation
复制标题
DOI：
10.1016/j.patcog.2010.10.001
复制
发表时间：
2011-03
期刊：
影响因子：
--
通讯作者：
Bingkun Bao;Bingbing Ni;Yadong Mu;Shuicheng Yan
中科院分区：
文献类型：
--
作者：
Bingkun Bao;Bingbing Ni;Yadong Mu;Shuicheng Yan
随着Flickr和Picasa等图片共享网站上图片数量的快速增长，迫切需要开发可扩展的多标签传播算法来进行图像索引、管理和检索。在图像语义区域层次上进行分析可以大大提高图像标注的性能。然而，区域级方法将数据规模增加到几个数量级，并对大多数现有算法提出了新的挑战。在这项工作中，我们提出了一个新的框架，有效地计算成对的图像相似性，通过积累的语义图像区域的信息。首先，每个图像被编码为基于多个图像分割的区域袋。其次，所有的图像区域被分成桶与有效的局部敏感哈希（LSH）方法，这保证了高碰撞概率的相似区域。每个图像的k-最近邻和相应的相似性可以有效地近似与这些索引补丁。最后，稀疏和区域感知的图像相似性矩阵被馈送到熵图正则化半监督学习算法的多标签扩展中[1]。结合起来，它们自然产生处理大规模数据集的能力。NUS-WIDE（260 k图像）和COREL-5 k数据集上的大量实验验证了我们提出的区域感知和可扩展多标签传播框架的有效性和效率。
With fast growing number of images on photo-sharing websites such as Flickr and Picasa, it is in urgent need to develop scalable multi-label propagation algorithms for image indexing, management and retrieval. It has been well acknowledged that analysis in semantic region level may greatly improve image annotation performance compared to that in the holistic image level. However, region level approach increases the data scale to several orders of magnitude and proposes new challenges to most existing algorithms. In this work, we present a novel framework to effectively compute pairwise image similarity by accumulating the information of semantic image regions. Firstly, each image is encoded as Bag-of-Regions based on multiple image segmentations. Secondly, all image regions are separated into buckets with efficient locality-sensitive hashing (LSH) method, which guarantees high collision probabilities for similar regions. The k-nearest neighbors of each image and the corresponding similarities can be efficiently approximated with these indexed patches. Lastly, the sparse and region-aware image similarity matrix is fed into the multi-label extension of the entropic graph regularized semi-supervised learning algorithm [1]. In combination they naturally yield the capability of handling large-scale dataset. Extensive experiments on NUS-WIDE (260k images) and COREL-5k datasets validate the effectiveness and efficiency of our proposed framework for region-aware and scalable multi-label propagation.