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 2010.13636cs.CVcs.LG
收藏

更少才是更多:从图分类视角使用更少代理的深度图度量学习

Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies

Xidian University(西安电子科技大学);Tencent AI Lab(腾讯人工智能实验室)

Yuehua Zhu, Muli Yang, Cheng Deng, Wei Liu

AI总结:

本文提出了一种基于图分类视角的深度图度量学习方法ProxyGML,通过使用更少的代理来提升模型性能和效率。

摘要:

深度度量学习在各种机器学习任务中起着关键作用。大多数先前的工作都局限于从小批量中采样,这无法精确表征嵌入空间的全局几何结构。尽管研究人员已经开发了代理和分类基于的方法来解决采样问题,但这些方法不可避免地会带来冗余的计算成本。在本文中,我们从图分类的视角提出了一种新的代理深度图度量学习(ProxyGML)方法,该方法使用更少的代理却能获得更好的综合性能。具体来说,多个全局代理被用来共同近似每个类别的原始数据点。为了高效捕捉局部邻居关系,少量这样的代理被自适应地选择,以构建这些代理与每个数据点之间的相似性子图。进一步,我们设计了一种新的反向标签传播算法,通过该算法根据真实标签调整邻居关系,从而在子图分类过程中学习到一个判别性的度量空间。在广泛使用的CUB-200-2011、Cars196和Stanford Online Products数据集上进行的大量实验表明,所提出的ProxyGML在有效性和效率方面均优于最先进的方法。源代码可在https://github.com/YuehuaZhu/ProxyGML上公开获取。

英文摘要:

Deep metric learning plays a key role in various machine learning tasks. Most of the previous works have been confined to sampling from a mini-batch, which cannot precisely characterize the global geometry of the embedding space. Although researchers have developed proxy- and classification-based methods to tackle the sampling issue, those methods inevitably incur a redundant computational cost. In this paper, we propose a novel Proxy-based deep Graph Metric Learning (ProxyGML) approach from the perspective of graph classification, which uses fewer proxies yet achieves better comprehensive performance. Specifically, multiple global proxies are leveraged to collectively approximate the original data points for each class. To efficiently capture local neighbor relationships, a small number of such proxies are adaptively selected to construct similarity subgraphs between these proxies and each data point. Further, we design a novel reverse label propagation algorithm, by which the neighbor relationships are adjusted according to ground-truth labels, so that a discriminative metric space can be learned during the process of subgraph classification. Extensive experiments carried out on widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate the superiority of the proposed ProxyGML over the state-of-the-art methods in terms of both effectiveness and efficiency. The source code is publicly available at https://github.com/YuehuaZhu/ProxyGML.

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。

↑