Few-example Logo Detection with Model Refinement

Bing Liu, Bing Li, Weiming Hu, Jinfeng Yang

2019

Abstract

Logo detection is a laborious but strong practicality task that has a variety of technology applications. Since the fundamental of state-of-the-art detectors, large-scale annotated datasets, is cost-consuming, few-example logo detection is imperative and thought-provoking. In this paper, a three-stage Few-example Logo Detection Refined System (FLDRS) is proposed to detect logo with a few annotated samples. Specifically, the proposed detector is first initialized using large-scale generic target detection dataset with annotations, such as ImageNet, then further updated with large amount of synthetic logo images, and finally refined with a few annotated real examples. To make synthetic data more closer to real scene, a copy-paste-blend strategy is also presented in our model which not only characterizes many kinds of possible logo transformations but also takes the environment attribute of the logo type into consideration. The superior performance in FlickLogo-32 dataset demonstrates the efficiency of the proposed FLDRS.

Paper Citation

in Harvard Style

Liu B., Li B., Hu W. and Yang J. (2019). Few-example Logo Detection with Model Refinement.In Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC, ISBN 978-989-758-357-5, pages 122-127. DOI: 10.5220/0008096901220127

in Bibtex Style

@conference{ctisc19,
author={Bing Liu and Bing Li and Weiming Hu and Jinfeng Yang},
title={Few-example Logo Detection with Model Refinement},
booktitle={Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC,},
year={2019},
pages={122-127},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008096901220127},
isbn={978-989-758-357-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Advances in Computer Technology, Information Science and Communications - Volume 1: CTISC,
TI - Few-example Logo Detection with Model Refinement
SN - 978-989-758-357-5
AU - Liu B.
AU - Li B.
AU - Hu W.
AU - Yang J.
PY - 2019
SP - 122
EP - 127
DO - 10.5220/0008096901220127