Distance-based online pairs generation method for metric networks training

Ivan V. Kondrashev; Alexander V. Sheshkus; Vladimir V. Arlazarov

doi:10.1117/12.2587175

4 January 2021 Distance-based online pairs generation method for metric networks training

Ivan V. Kondrashev, Alexander V. Sheshkus, Vladimir V. Arlazarov

Proceedings Volume 11605, Thirteenth International Conference on Machine Vision; 1160508 (2021) https://doi.org/10.1117/12.2587175
Event: Thirteenth International Conference on Machine Vision, 2020, Rome, Italy

Abstract

In this work, we consider the pairs generation algorithm based on the distances between elements in metric space. The right generation of training data is an actual issue, and its solution leads to better neural network learning. Understanding the properties of the source data, we can select pairs for training in such a way that the network will pay more attention to elements that are close in the metric space and have different classes. However, the problem arises when these properties are difficult to extract from the data and a more universal pairs generation method is needed. Our method generates pairs using the results of the network from previous iterations, in parallel with the training process itself. Thus, we do not need to evaluate the properties of elements ourselves, and we can use absolutely any data as learning objects. We demonstrate this approach using the example of Korean character recognition, and also compare it with other commonly used pair generation methods.

Citation Download Citation

Ivan V. Kondrashev, Alexander V. Sheshkus, and Vladimir V. Arlazarov "Distance-based online pairs generation method for metric networks training", Proc. SPIE 11605, Thirteenth International Conference on Machine Vision, 1160508 (4 January 2021); https://doi.org/10.1117/12.2587175

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