DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features

Abstract

Image Retrieval is a fundamental task of obtaining images similar to the query one from a database. A common image retrieval practice is to firstly retrieve candidate images via similarity search using global image features and then re-rank the candidates by leveraging their local features. Previous learning-based studies mainly focus on either global or local image representation learning to tackle the retrieval task. In this paper, we abandon the two-stage paradigm and seek to design an effective single-stage solution by integrating local and global information inside images into compact image representations. Specifically, we propose a Deep Orthogonal Local and Global (DOLG) information fusion framework for end-to-end image retrieval. It attentively extracts representative local information with multi-atrous convolutions and self-attention at first. Components orthogonal to the global image representation are then extracted from the local information. At last, the orthogonal compone

Stats

• citations133
• S2 citations—
• github stars0
• HF likes0
• heat score15.95
• arxiv keyyang2021dolg

Related papers

• Unifying Deep Local And Global Features For Image Search (2020)28.10
• DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Global-to-local Or Local-to-global? Enhancing Image Retrieval With Efficient Local Search And Effective Global Re-ranking (2025)0.00
• Efficient Large-scale Image Retrieval With Deep Feature Orthogonality And Hybrid-swin-transformers (2021)0.00
• Coarse2fine: Two-layer Fusion For Image Retrieval (2016)0.00
• Coarse-to-fine: Learning Compact Discriminative Representation For Single-stage Image Retrieval (2023)9.35
• Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11