Zheng Min, Geng Yangliao, Li Qingyong
Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China.
Entropy (Basel). 2022 Jan 20;24(2):156. doi: 10.3390/e24020156.
Fine-grained image retrieval aims at searching relevant images among fine-grained classes given a query. The main difficulty of this task derives from the small interclass distinction and the large intraclass variance of fine-grained images, posing severe challenges to the methods that only resort to global or local features. In this paper, we propose a novel fine-grained image retrieval method, where global-local aware feature representation is learned. Specifically, the global feature is extracted by selecting the most relevant deep descriptors. Meanwhile, we explore the intrinsic relationship of different parts via the frequent pattern mining, thus obtaining the representative local feature. Further, an aggregation feature that learns global-local aware feature representation is designed. Consequently, the discriminative ability among different fine-grained classes is enhanced. We evaluate the proposed method on five popular fine-grained datasets. Extensive experimental results demonstrate that the performance of fine-grained image retrieval is improved with the proposed global-local aware representation.
细粒度图像检索旨在给定一个查询的情况下，在细粒度类别中搜索相关图像。这项任务的主要困难源于细粒度图像的类间差异小和类内方差大，这给仅依靠全局或局部特征的方法带来了严峻挑战。在本文中，我们提出了一种新颖的细粒度图像检索方法，该方法学习全局-局部感知特征表示。具体而言，通过选择最相关的深度描述符来提取全局特征。同时，我们通过频繁模式挖掘探索不同部分的内在关系，从而获得具有代表性的局部特征。此外，还设计了一种学习全局-局部感知特征表示的聚合特征。因此，增强了不同细粒度类别之间的判别能力。我们在五个流行的细粒度数据集上评估了所提出的方法。大量实验结果表明，所提出的全局-局部感知表示提高了细粒度图像检索的性能。
