Coarse2Fine: Two-Layer Fusion For Image Retrieval

07/04/2016
by   Gaipeng Kong, et al.
0

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 method outperforms recent fusion methods in terms of storage consumption and computation complexity, and that the accuracy is competitive to the state-of-the-arts.

READ FULL TEXT

page 1

page 3

page 8

research
08/06/2021

DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features

Image Retrieval is a fundamental task of obtaining images similar to the...
research
10/31/2018

Query Adaptive Late Fusion for Image Retrieval

Feature fusion is a commonly used strategy in image retrieval tasks, whi...
research
03/16/2022

Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects

In this paper, we tackle the task of estimating the 3D orientation of pr...
research
09/24/2016

Perceptual uniform descriptor and Ranking on manifold: A bridge between image representation and ranking for image retrieval

Incompatibility of image descriptor and ranking is always neglected in i...
research
07/14/2017

Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval

Existing manifold learning methods are not appropriate for image retriev...
research
06/25/2022

Inverted Semantic-Index for Image Retrieval

This paper addresses the construction of inverted index for large-scale ...
research
09/06/2017

Cross-Domain Image Retrieval with Attention Modeling

With the proliferation of e-commerce websites and the ubiquitousness of ...

Please sign up or login with your details

Forgot password? Click here to reset