Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Image Retrieval Re-ranking using Graph Neural Networks

Hanning, Gustav LU (2024) In Master’s Theses in Mathematical Sciences FMAM02 20232
Mathematics (Faculty of Engineering)
Abstract
Image retrieval is the task of finding images in a database similar to a given query image. The retrieved images, typically a small subset of the entire database, are initially ordered based on their similarity with the query. They can subsequently be re-ranked to improve the retrieval accuracy. Database images that are relevant to the query should increase in rank and vice versa.

In this thesis the re-ranking process is modeled as a graph neural network. The nodes of the graph are the query and retrieved database images. For each node an affinity vector is computed which encodes the visual similarity between the image and a set of anchor images. The vectors are refined by message passing between nodes, using self-attention. Database... (More)
Image retrieval is the task of finding images in a database similar to a given query image. The retrieved images, typically a small subset of the entire database, are initially ordered based on their similarity with the query. They can subsequently be re-ranked to improve the retrieval accuracy. Database images that are relevant to the query should increase in rank and vice versa.

In this thesis the re-ranking process is modeled as a graph neural network. The nodes of the graph are the query and retrieved database images. For each node an affinity vector is computed which encodes the visual similarity between the image and a set of anchor images. The vectors are refined by message passing between nodes, using self-attention. Database images are re-ranked according to the similarity between their refined affinity vector and that of the query.

The network is trained on a large-scale dataset and evaluated against three other re-ranking algorithms. Results show that the method proposed in the thesis achieves significantly higher precision. (Less)
Please use this url to cite or link to this publication:
author
Hanning, Gustav LU
supervisor
organization
course
FMAM02 20232
year
type
H2 - Master's Degree (Two Years)
subject
publication/series
Master’s Theses in Mathematical Sciences
report number
2024:E18
ISSN
1404-6342
other publication id
LUTFMA-3531-2024
language
English
id
9151796
date added to LUP
2024-05-31 11:08:32
date last changed
2024-05-31 11:08:32
@misc{9151796,
  abstract     = {{Image retrieval is the task of finding images in a database similar to a given query image. The retrieved images, typically a small subset of the entire database, are initially ordered based on their similarity with the query. They can subsequently be re-ranked to improve the retrieval accuracy. Database images that are relevant to the query should increase in rank and vice versa.

In this thesis the re-ranking process is modeled as a graph neural network. The nodes of the graph are the query and retrieved database images. For each node an affinity vector is computed which encodes the visual similarity between the image and a set of anchor images. The vectors are refined by message passing between nodes, using self-attention. Database images are re-ranked according to the similarity between their refined affinity vector and that of the query.

The network is trained on a large-scale dataset and evaluated against three other re-ranking algorithms. Results show that the method proposed in the thesis achieves significantly higher precision.}},
  author       = {{Hanning, Gustav}},
  issn         = {{1404-6342}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Master’s Theses in Mathematical Sciences}},
  title        = {{Image Retrieval Re-ranking using Graph Neural Networks}},
  year         = {{2024}},
}