Dr Kyle Martin k.martin3@rgu.ac.uk
Lecturer
Informed pair selection for self-paced metric learning in Siamese neural networks.
Martin, Kyle; Wiratunga, Nirmalie; Massie, Stewart; Clos, J�r�mie
Authors
Professor Nirmalie Wiratunga n.wiratunga@rgu.ac.uk
Associate Dean for Research
Dr Stewart Massie s.massie@rgu.ac.uk
Associate Professor
J�r�mie Clos
Contributors
Max Bramer
Editor
Miltos Petridis
Editor
Abstract
Siamese Neural Networks (SNNs) are deep metric learners that use paired instance comparisons to learn similarity. The neural feature maps learnt in this way provide useful representations for classification tasks. Learning in SNNs is not reliant on explicit class knowledge; instead they require knowledge about the relationship between pairs. Though often ignored, we have found that appropriate pair selection is crucial to maximising training efficiency, particularly in scenarios where examples are limited. In this paper, we study the role of informed pair selection and propose a 2-phased strategy of exploration and exploitation. Random sampling provides the needed coverage for exploration, while areas of uncertainty modeled by neighbourhood properties of the pairs drive exploitation. We adopt curriculum learning to organise the ordering of pairs at training time using similarity knowledge as a heuristic for pair sorting. The results of our experimental evaluation show that these strategies are key to optimising training.
Citation
MARTIN, K., WIRATUNGA, N., MASSIE, S. and CLOS, J. 2018. Informed pair selection for self-paced metric learning in Siamese neural networks. In Bramer, M. and Petridis, M. (eds.) Artificial intelligence XXXV: proceedings of the 38th British Computer Society's Specialist Group on Artificial Intelligence (SGAI) International conference on innovative techniques and applications of artificial intelligence (AI-2018), 11-13 December 2018, Cambridge, UK. Lecture notes in computer science, 11311. Cham: Springer [online], pages 34-49. Available from: https://doi.org/10.1007/978-3-030-04191-5_3
Conference Name | 38th British Computer Society's Specialist Group on Artificial Intelligence (SGAI) International conference on innovative techniques and applications of artificial intelligence (AI-2018) |
---|---|
Conference Location | Cambridge, UK |
Start Date | Dec 11, 2018 |
End Date | Dec 13, 2018 |
Acceptance Date | Sep 3, 2018 |
Online Publication Date | Nov 16, 2018 |
Publication Date | Dec 31, 2018 |
Deposit Date | Jan 21, 2019 |
Publicly Available Date | Mar 29, 2024 |
Publisher | Springer |
Pages | 34-49 |
Series Title | Lecture notes in computer science |
Series Number | 11311 |
Series ISSN | 0302-9743 |
Book Title | Artificial intelligence XXXV |
ISBN | 9783030041908 |
DOI | https://doi.org/10.1007/978-3-030-04191-5_3 |
Keywords | Deep learning; Siamese neural networks; Active learning; Case based reasoning; Machine learning; Metric learning |
Public URL | http://hdl.handle.net/10059/3269 |
Files
MARTIN 2018 Informed pair selection
(434 Kb)
PDF
Publisher Licence URL
https://creativecommons.org/licenses/by-nc/4.0/
You might also like
iSee: intelligent sharing of explanation experience of users for users.
(2023)
Conference Proceeding
iSee: demonstration video. [video recording]
(2023)
Digital Artefact
Adapting semantic similarity methods for case-based reasoning in the Cloud.
(2022)
Conference Proceeding
How close is too close? Role of feature attributions in discovering counterfactual explanations.
(2022)
Conference Proceeding
A case-based approach for content planning in data-to-text generation.
(2022)
Conference Proceeding
Downloadable Citations
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search