loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Kaiyu Suzuki 1 ; Yasushi Kambayashi 2 and Tomofumi Matsuzawa 1

Affiliations: 1 Department of Information Sciences, Tokyo University of Science, Japan ; 2 Department of Computer Information Engineering, Nippon Institute of Technology, Japan

Keyword(s): Representation Learning, Machine Learning, Neural Networks, Multi-agent Intelligent Systems, Robustness.

Abstract: One of the most important tasks for multi-agents such as drones is to automatically make decisions based on images captured by on-board cameras. These agents must be highly accurate and reliable. For this purpose, we applied k-fold cross validation to the task of classifying images using deep learning, which is a method that compares and evaluates models appropriately model of a given problem; this technique is easy to understand and easy to implement, and it produces results in lower bias estimates. However, k-fold cross validation reduces the amount of data per neural network, which reduces the accuracy. In order to address this problem, we propose CrossSiam. CrossSiam is a one of the representation learning methods to train feature encoders to mimic the embedding space of the validation data of each neural network. We show that the proposed method has a higher classification accuracy than the ParaSiam (baseline). This approach can be very important in the field where reliability i s required, such as automated vehicles and drones in disaster situations. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.15.14.245

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Suzuki, K.; Kambayashi, Y. and Matsuzawa, T. (2022). CrossSiam: k-Fold Cross Representation Learning. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: SDMIS; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 541-547. DOI: 10.5220/0010972500003116

@conference{sdmis22,
author={Kaiyu Suzuki. and Yasushi Kambayashi. and Tomofumi Matsuzawa.},
title={CrossSiam: k-Fold Cross Representation Learning},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: SDMIS},
year={2022},
pages={541-547},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010972500003116},
isbn={978-989-758-547-0},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: SDMIS
TI - CrossSiam: k-Fold Cross Representation Learning
SN - 978-989-758-547-0
IS - 2184-433X
AU - Suzuki, K.
AU - Kambayashi, Y.
AU - Matsuzawa, T.
PY - 2022
SP - 541
EP - 547
DO - 10.5220/0010972500003116
PB - SciTePress