Version 1
: Received: 31 October 2024 / Approved: 31 October 2024 / Online: 1 November 2024 (08:54:23 CET)
How to cite:
Mokin, A.; Sheshkus, A.; Arlazarov, V. L. Auto-probabilistic Mining Method for Siamese Neural Networks Training. Preprints2024, 2024110001. https://doi.org/10.20944/preprints202411.0001.v1
Mokin, A.; Sheshkus, A.; Arlazarov, V. L. Auto-probabilistic Mining Method for Siamese Neural Networks Training. Preprints 2024, 2024110001. https://doi.org/10.20944/preprints202411.0001.v1
Mokin, A.; Sheshkus, A.; Arlazarov, V. L. Auto-probabilistic Mining Method for Siamese Neural Networks Training. Preprints2024, 2024110001. https://doi.org/10.20944/preprints202411.0001.v1
APA Style
Mokin, A., Sheshkus, A., & Arlazarov, V. L. (2024). Auto-probabilistic Mining Method for Siamese Neural Networks Training. Preprints. https://doi.org/10.20944/preprints202411.0001.v1
Chicago/Turabian Style
Mokin, A., Alexander Sheshkus and Vladimir L. Arlazarov. 2024 "Auto-probabilistic Mining Method for Siamese Neural Networks Training" Preprints. https://doi.org/10.20944/preprints202411.0001.v1
Abstract
In this paper we present a novel auto-probabilistic mining method designed to enhance the training process of Siamese neural networks. The proposed method demonstrates significant efficiency, particularly in scenarios characterized by limited data and computational resource. The study incorporates the application of the newly developed mining method in conjunction with a previously introduced auto-clustering technique. Comparative experiments are conducted both with and without the integration of the proposed method, highlighting its impact on overall performance. Additionally, the research introduces a novel metric loss to further refine the training process taking into account the drawbacks of existing loss functions applying for metric learning. During the experimentation phase, validation is conducted on the printed Hangul character PHD08 database and Omniglot. This validation provides valuable insights into the performance and effectiveness of the proposed methods.
Keywords
deep metric learning; optical character recognition; pattern recognition
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
