Coarse2fine: Two-layer Fusion For Image Retrieval

Abstract

This paper addresses the problem of large-scale image retrieval. We propose a two-layer fusion method which takes advantage of global and local cues and ranks database images from coarse to fine (C2F). Departing from the previous methods fusing multiple image descriptors simultaneously, C2F is featured by a layered procedure composed by filtering and refining. In particular, C2F consists of three components. 1) Distractor filtering. With holistic representations, noise images are filtered out from the database, so the number of candidate images to be used for comparison with the query can be greatly reduced. 2) Adaptive weighting. For a certain query, the similarity of candidate images can be estimated by holistic similarity scores in complementary to the local ones. 3) Candidate refining. Accurate retrieval is conducted via local features, combining the pre-computed adaptive weights. Experiments are presented on two benchmarks, *i.e.,* Holidays and Ukbench datasets. We show that our m

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykong2016coarse2fine

Related papers

• Coarse-to-fine: Learning Compact Discriminative Representation For Single-stage Image Retrieval (2023)9.35
• Query Adaptive Late Fusion For Image Retrieval (2018)0.00
• Detailfusion: A Dual-branch Framework With Detail Enhancement For Composed Image Retrieval (2025)0.00
• DAFM: Dynamic Adaptive Fusion For Multi-model Collaboration In Composed Image Retrieval (2025)0.00
• An Efficient Image Retrieval Based On Fusion Of Low-level Visual Features (2018)3.58
• Content-based Image Retrieval Based On Late Fusion Of Binary And Local Descriptors (2017)4.52
• DOLG: Single-stage Image Retrieval With Deep Orthogonal Fusion Of Local And Global Features (2021)15.95
• Three Tiers Neighborhood Graph And Multi-graph Fusion Ranking For Multi-feature Image Retrieval: A Manifold Aspect (2016)0.00