Revisiting Local Descriptors via Frequent Pattern Mining for Fine-Grained Image Retrieval

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.

Automated summary

This paper proposes a novel fine-grained image retrieval method that enhances the discriminative ability among different fine-grained classes by learning a global-local aware feature representation and exploring the intrinsic relationship of different parts via frequent pattern mining to obtain representative local features. Experimental results demonstrate the improved performance of fine-grained image retrieval with the proposed method.