Dr Anjana Wijekoon a.wijekoon1@rgu.ac.uk
Research Fellow B
Dr Anjana Wijekoon a.wijekoon1@rgu.ac.uk
Research Fellow B
Professor Nirmalie Wiratunga n.wiratunga@rgu.ac.uk
Associate Dean for Research
Sadiq Sani
Kyle Martin
Editor
Professor Nirmalie Wiratunga n.wiratunga@rgu.ac.uk
Editor
Leslie S. Smith
Editor
A real-world solution for Human Activity Recognition (HAR) should cover a variety of activities. However training a model to cover each and every possible activity is not practical. Instead we need a solution that can adapt its learning to unseen activities; referred to as open-ended HAR. Recent advancements in deep learning have increasingly begun to focus on the need to learn from few examples, referred to as k-shot learning and to go beyond this to transfer that learning to situations with unseen classes, referred to as zero-shot learning. The latter is particularly relevant to our research in open-ended HAR; and as yet remains unexplored. This paper presents our preliminary work with Zero-shot Learning (ZSL) with a Matching Network to address open-ended HAR. A Matching Network has the desirable property of learning with few examples and so is well suited to explorations in ZSL. We evaluate Matching Networks for ZSL with a HAR dataset. We propose the use of a variable length support set at test time to overcome the search for the best support set combination that currently plagues the fixed length support set size used by matching nets. Our results show that the variable length approach to be an effective strategy to maintain accuracy whilst avoiding the combinatorial search for the best class combination to form the support set.
WIJEKOON, A., WIRATUNGA, N. and SANI, S. 2018. Zero-shot learning with matching networks for open-ended human activity recognition. In Martin, K., Wiratunga, N. and Smith, L.S. (eds.) Proceedings of the 2018 Scottish Informatics and Computer Science Alliance (SCISA) workshop on reasoning, learning and explainability (ReaLX 2018), 27 June 2018, Aberdeen, UK. CEUR workshop proceedings, 2151. Aachen: CEUR-WS [online], session 2, paper 4. Available from: http://ceur-ws.org/Vol-2151/Paper_S9.pdf
Conference Name | 2018 Scottish Informatics and Computer Science Alliance (SCISA) workshop on reasoning, learning and explainability (ReaLX 2018) |
---|---|
Conference Location | Aberdeen, UK |
Start Date | Jun 27, 2018 |
Acceptance Date | Jun 8, 2018 |
Online Publication Date | Jun 27, 2018 |
Publication Date | Jul 30, 2018 |
Deposit Date | Aug 31, 2018 |
Publicly Available Date | Aug 31, 2018 |
Print ISSN | 1613-0073 |
Publisher | CEUR Workshop Proceedings |
Series Title | CEUR workshop proceedings |
Series Number | 2151 |
Series ISSN | 1613-0073 |
Keywords | Zeroshot learning; Matching networks; Openended HAR |
Public URL | http://hdl.handle.net/10059/3097 |
Publisher URL | http://ceur-ws.org/Vol-2151/Paper_S9.pdf |
WIJEKOON 2018 Zero-shot learning (VOR)
(1.1 Mb)
PDF
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
Clinical dialogue transcription error correction using Seq2Seq models.
(2022)
Working Paper
About OpenAIR@RGU
Administrator e-mail: publications@rgu.ac.uk
This application uses the following open-source libraries:
Apache License Version 2.0 (http://www.apache.org/licenses/)
Apache License Version 2.0 (http://www.apache.org/licenses/)
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