Timezone: »

Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
Yuehua Zhu · Muli Yang · Cheng Deng · Wei Liu

Tue Dec 08 08:10 PM -- 08:20 PM (PST) @ Orals & Spotlights: Vision Applications

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 \url{https://github.com/YuehuaZhu/ProxyGML}.

Author Information

Yuehua Zhu (Xidian University)
Muli Yang (Xidian University)
Cheng Deng (Xidian University)
Wei Liu (Tencent AI Lab)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors