Informed pair selection for self-paced metric learning in Siamese neural networks.
MetadataShow full item record
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) annual international artificial intelligence conference (AI-2018), 11-13 December 2018, Cambridge, UK. Lecture notes in artificial intelligence, 11311. Cham: Springer [online], pages 34-49. Available from: https://doi.org/10.1007/978-3-030-04191-5_3
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.
Permalink for this recordhttp://hdl.handle.net/10059/3269
Collections in which this item appears
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc/4.0
Showing items related by title, author, creator and subject.
Fulford, Heather; Bailey, Moira (Academic Conferences and Publishing International Limited http://www.proceedings.com/24280.html, 2014-09-18)FULFORD, H. and BAILEY, M. 2014. Journals and jottings on entrepreneurial learning journeys. In Galbraith, B. (ed.) Proceedings of the 9th European conference on innovation and entrepreneurship (ECIE 2014), 18-19 September 2014, Belfast, UK. Reading: Academic Conferences Ltd [online], pages 198-206. Available from: http://www.proceedings.com/24280.htmlReview of relevant literature highlighted that entrepreneurs need help to reflect on, and make sense of, the challenges and opportunities that occur during the entrepreneurial process. For students who are unfamiliar with ...
Hussein, Ahmed; Gaber, Mohamed Medhat; Elyan, Eyad; Jayne, Chrisina (ACM https://doi.org/10.1145/3054912, 2017-04-11)HUSSEIN, A., GABER, M.M., ELYAN, E. and JAYNE, C. 2017 Imitation learning: a survey of learning methods. ACM computing surveys [online], 50(2), article 21. Available from: https://doi.org/10.1145/3054912Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of ...
Hussein, Ahmed; Elyan, Eyad; Gaber, Mohamed Medhat; Jayne, Chrisina (Springer https://doi.org/10.1007/s00521-017-3241-z, 2017-12-04)HUSSEIN, A., ELYAN, E., GABER, M.M. and JAYNE, C. 2018. Deep imitation learning for 3D navigation tasks. Neural computing and applications [online], 29(7), pages 389-404. Available from: https://doi.org/10.1007/s00521-017-3241-zDeep learning techniques have shown success in learning from raw high dimensional data in various applications. While deep reinforcement learning is recently gaining popularity as a method to train intelligent agents, ...