Auto-clustering pairs generation method for Siamese neural networks training

Arseniy K. Mokin; Alexander V. Gayer; Alexander V. Sheshkus; Vladimir L. Arlazarov

doi:10.1117/12.2623139

4 March 2022 Auto-clustering pairs generation method for Siamese neural networks training

Arseniy K. Mokin, Alexander V. Gayer, Alexander V. Sheshkus, Vladimir L. Arlazarov

Proceedings Volume 12084, Fourteenth International Conference on Machine Vision (ICMV 2021); 120841A (2022) https://doi.org/10.1117/12.2623139
Event: Fourteenth International Conference on Machine Vision (ICMV 2021), 2021, Rome, Italy

Abstract

In this work, we present the auto-clustering method which can be used for pattern recognition tasks and applied to the training of a metric convolutional neural network. The main idea is that the algorithm creates clusters consisting of classes similar from a network’s point of view. The usage of clusters allows the network to pay more attention to classes that are hard to differ. This method improves the generation of pairs during the training process, which is a current problem because the optimal generation of data significantly affects the quality of training. The algorithm works in parallel with the training process and is fully automatic. To evaluate this method we chose the Korean alphabet with the corresponding PHD08 dataset and compared our auto-clustering with random-mining, hard-mining, distance-based mining. Opensource framework Tesseract OCR 4.0.0 was also considered to evaluate the baseline.

Citation Download Citation

Arseniy K. Mokin, Alexander V. Gayer, Alexander V. Sheshkus, and Vladimir L. Arlazarov "Auto-clustering pairs generation method for Siamese neural networks training", Proc. SPIE 12084, Fourteenth International Conference on Machine Vision (ICMV 2021), 120841A (4 March 2022); https://doi.org/10.1117/12.2623139

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available