DVF: Advancing Robust And Accurate Fine-grained Image Retrieval With Retrieval Guidelines

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 strategy (G3). Following G1 and G2, we design a novel Dual Visual Filtering mechanism for the plain visual transformer, denoted as DVF, to capture subcategory-specific discrepancies. Specifically, the dual visual filtering mechanism comprises an object-oriented module and a semantic-oriented module. These components serve to magnify objects and identify discriminative regions,

Stats

• citations15
• S2 citations—
• github stars0
• HF likes0
• heat score9.03
• arxiv keyjiang2024dvf

Related papers

• Fine-grained Image Retrieval Via Dual-vision Adaptation (2025)0.00
• Adversarial Reconstruction Feedback For Robust Fine-grained Generalization (2025)0.00
• One-shot Fine-grained Instance Retrieval (2017)10.35
• Language-driven Fine-grained Retrieval (2025)0.00
• Unifgvc: Universal Training-free Few-shot Fine-grained Vision Classification Via Attribute-aware Multimodal Retrieval (2025)0.00
• Adaptive Fine-grained Sketch-based Image Retrieval (2022)9.76
• FIGROTD: A Friendly-to-handle Dataset For Image Guided Retrieval With Optional Text (2025)0.00
• Coarse-to-fine: Learning Compact Discriminative Representation For Single-stage Image Retrieval (2023)9.35