Visual Re-ranking with Non-visual Side Information
Hanning, Gustav LU
; Flood, Gabrielle
LU
and Larsson, Viktor
LU
(2025)
23rd Scandinavian Conference on Image Analysis, SCIA 2025
In Lecture Notes in Computer Science
15725 LNCS.
p.310-323
- Abstract
The standard approach for visual place recognition is to use global image descriptors to retrieve the most similar database images for a given query image. The results can then be further improved with re-ranking methods that re-order the top scoring images. However, existing methods focus on re-ranking based on the same image descriptors that were used for the initial retrieval, which we argue provides limited additional signal. In this work we propose Generalized Contextual Similarity Aggregation (GCSA), which is a graph neural network-based re-ranking method that, in addition to the visual descriptors, can leverage other types of available side information. This can for example be other sensor data (such as signal strength of nearby... (More)
The standard approach for visual place recognition is to use global image descriptors to retrieve the most similar database images for a given query image. The results can then be further improved with re-ranking methods that re-order the top scoring images. However, existing methods focus on re-ranking based on the same image descriptors that were used for the initial retrieval, which we argue provides limited additional signal. In this work we propose Generalized Contextual Similarity Aggregation (GCSA), which is a graph neural network-based re-ranking method that, in addition to the visual descriptors, can leverage other types of available side information. This can for example be other sensor data (such as signal strength of nearby WiFi or BlueTooth endpoints) or geometric properties such as camera poses for database images. In many applications this information is already present or can be acquired with low effort. Our architecture leverages the concept of affinity vectors to allow for a shared encoding of the heterogeneous multi-modal input. Two large-scale datasets, covering both outdoor and indoor localization scenarios, are utilized for training and evaluation. In experiments we show significant improvement not only on image retrieval metrics, but also for the downstream visual localization task.
(Less)
- author
- Hanning, Gustav
LU
; Flood, Gabrielle
LU
and Larsson, Viktor
LU
- organization
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- GNN, Image retrieval re-ranking, Visual localization
- host publication
- Image Analysis - 23rd Scandinavian Conference, SCIA 2025, Proceedings
- series title
- Lecture Notes in Computer Science
- editor
- Petersen, Jens and Dahl, Vedrana Andersen
- volume
- 15725 LNCS
- pages
- 14 pages
- publisher
- Springer Science and Business Media B.V.
- conference name
- 23rd Scandinavian Conference on Image Analysis, SCIA 2025
- conference location
- Reykjavik, Iceland
- conference dates
- 2025-06-23 - 2025-06-25
- external identifiers
-
- scopus:105009845345
- ISSN
- 0302-9743
- 1611-3349
- ISBN
- 9783031959103
- DOI
- 10.1007/978-3-031-95911-0_22
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
- id
- 4b7f1768-a803-4403-957d-3ef8381ba536
- date added to LUP
- 2025-12-22 10:30:45
- date last changed
- 2025-12-23 03:51:35
@inproceedings{4b7f1768-a803-4403-957d-3ef8381ba536,
abstract = {{<p>The standard approach for visual place recognition is to use global image descriptors to retrieve the most similar database images for a given query image. The results can then be further improved with re-ranking methods that re-order the top scoring images. However, existing methods focus on re-ranking based on the same image descriptors that were used for the initial retrieval, which we argue provides limited additional signal. In this work we propose Generalized Contextual Similarity Aggregation (GCSA), which is a graph neural network-based re-ranking method that, in addition to the visual descriptors, can leverage other types of available side information. This can for example be other sensor data (such as signal strength of nearby WiFi or BlueTooth endpoints) or geometric properties such as camera poses for database images. In many applications this information is already present or can be acquired with low effort. Our architecture leverages the concept of affinity vectors to allow for a shared encoding of the heterogeneous multi-modal input. Two large-scale datasets, covering both outdoor and indoor localization scenarios, are utilized for training and evaluation. In experiments we show significant improvement not only on image retrieval metrics, but also for the downstream visual localization task.</p>}},
author = {{Hanning, Gustav and Flood, Gabrielle and Larsson, Viktor}},
booktitle = {{Image Analysis - 23rd Scandinavian Conference, SCIA 2025, Proceedings}},
editor = {{Petersen, Jens and Dahl, Vedrana Andersen}},
isbn = {{9783031959103}},
issn = {{0302-9743}},
keywords = {{GNN; Image retrieval re-ranking; Visual localization}},
language = {{eng}},
pages = {{310--323}},
publisher = {{Springer Science and Business Media B.V.}},
series = {{Lecture Notes in Computer Science}},
title = {{Visual Re-ranking with Non-visual Side Information}},
url = {{http://dx.doi.org/10.1007/978-3-031-95911-0_22}},
doi = {{10.1007/978-3-031-95911-0_22}},
volume = {{15725 LNCS}},
year = {{2025}},
}