Evaluation of Transfer Learning Techniques for Classification and Localization of Marine Animals

Parmeet Singh, Mae Seto

Abstract

The objective is to evaluate methods for simultaneous classification and localization towards a better size estimate of marine animals in still images. Marine animals in such images vary in orientations and size. It is challenging to create a bounding box that predicts the shape of the object. We compare axis-aligned and rotatable bounding box techniques for size estimation.

Download


Paper Citation


in Harvard Style

Singh P. and Seto M. (2019). Evaluation of Transfer Learning Techniques for Classification and Localization of Marine Animals.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-354-4, pages 169-176. DOI: 10.5220/0007390201690176


in Bibtex Style

@conference{visapp19,
author={Parmeet Singh and Mae Seto},
title={Evaluation of Transfer Learning Techniques for Classification and Localization of Marine Animals},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2019},
pages={169-176},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007390201690176},
isbn={978-989-758-354-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Evaluation of Transfer Learning Techniques for Classification and Localization of Marine Animals
SN - 978-989-758-354-4
AU - Singh P.
AU - Seto M.
PY - 2019
SP - 169
EP - 176
DO - 10.5220/0007390201690176