Coarse-to-fine: Learning Compact Discriminative Representation For Single-stage Image Retrieval

Abstract

Image retrieval targets to find images from a database that are visually similar to the query image. Two-stage methods following retrieve-and-rerank paradigm have achieved excellent performance, but their separate local and global modules are inefficient to real-world applications. To better trade-off retrieval efficiency and accuracy, some approaches fuse global and local feature into a joint representation to perform single-stage image retrieval. However, they are still challenging due to various situations to tackle, \(e.g.\), background, occlusion and viewpoint. In this work, we design a Coarse-to-Fine framework to learn Compact Discriminative representation (CFCD) for end-to-end single-stage image retrieval-requiring only image-level labels. Specifically, we first design a novel adaptive softmax-based loss which dynamically tunes its scale and margin within each mini-batch and increases them progressively to strengthen supervision during training and intra-class compactness. Furth

Stats

• citations6
• S2 citations—
• github stars31
• HF likes0
• heat score9.35
• arxiv keyzhu2023coarse

Related papers

• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• Coarse2fine: Two-layer Fusion For Image Retrieval (2016)0.00
• Unicom: Universal And Compact Representation Learning For Image Retrieval (2023)5.70
• Fast-then-fine: A Two-stage Framework With Multi-granular Representation For Cross-modal Retrieval In Remote Sensing (2026)0.00
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Re-rank Coarse Classification With Local Region Enhanced Features For Fine-grained Image Recognition (2021)0.00
• DALG: Deep Attentive Local And Global Modeling For Image Retrieval (2022)0.00
• DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features (2021)15.95