Unifying Deep Local And Global Features For Image Search

Abstract

Image retrieval is the problem of searching an image database for items that are similar to a query image. To address this task, two main types of image representations have been studied: global and local image features. In this work, our key contribution is to unify global and local features into a single deep model, enabling accurate retrieval with efficient feature extraction. We refer to the new model as DELG, standing for DEep Local and Global features. We leverage lessons from recent feature learning work and propose a model that combines generalized mean pooling for global features and attentive selection for local features. The entire network can be learned end-to-end by carefully balancing the gradient flow between two heads -- requiring only image-level labels. We also introduce an autoencoder-based dimensionality reduction technique for local features, which is integrated into the model, improving training efficiency and matching performance. Comprehensive experiments show t

Stats

• citations276
• S2 citations—
• github stars77667
• HF likes0
• heat score28.10
• arxiv keycao2020unifying

Related papers

• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00
• Learning Super-features For Image Retrieval (2022)4.31
• DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features (2021)15.95
• Large-scale Image Retrieval With Attentive Deep Local Features (2016)30.63
• Global Features Are All You Need For Image Retrieval And Reranking (2023)17.53
• Global-to-local Or Local-to-global? Enhancing Image Retrieval With Efficient Local Search And Effective Global Re-ranking (2025)0.00
• Aggregated Deep Local Features For Remote Sensing Image Retrieval (2019)14.11