DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelines

arXiv:2404.15771v1 Announce Type: new
Abstract: Fine-grained image retrieval (FGIR) is to learn visual representations that distinguish visually similar objects while maintaining generalization. Existing methods propose to generate discriminative features, but rarely consider the particularity of the FGIR task itself. This paper presents a meticulous analysis leading to the proposal of practical guidelines to identify subcategory-specific discrepancies and generate discriminative features to design effective FGIR models. These guidelines include emphasizing the object (G1), highlighting subcategory-specific discrepancies (G2), and employing effective training …

abstract analysis arxiv cs.cv cs.mm features fine-grained generate guidelines image learn objects paper retrieval robust type visual while