@inproceedings{1be0a06fdf4d4e6dab010b03a28c41c4,
title = "Learning an object detector using zoomed object regions",
abstract = "The single shot multi-box detector (SSD) is one of the first real-time detectors, which uses a convolutional neural network (CNN) and achieves the state-of-the-art detection performance. However, owing to the semantic gap between each feature layer of CNN, the SSD has a room for improvement. In this paper, we propose a novel training scheme to enhance the performance of the SSD. In object detection, ground truth (GT) box is a bounding box enclosing an object boundary. To improve the semantic level of the feature map, we generate additional GT boxes by zooming in to and out from the original GT boxes. Experimental results show that the SSD trained with our scheme outperforms the original one on public dataset.",
keywords = "Computer vision, Neural network, Object detection",
author = "Cho, {Sung Jin} and Kim, {Seung Wook} and Uhm, {Kwang Hyun} and Kook, {Hyong Keun} and Ko, {Sung Jea}",
note = "Funding Information: This work was supported by the Technology Innovation Program (or Industrial Strategic Technology Development Program) (10082585, Development of deep learning-based open EV platform technology capable of autonomous driving) funded By the Ministry of Trade, Industry & Energy (MOTIE, Korea). Publisher Copyright: {\textcopyright} 2019 Institute of Electronics and Information Engineers (IEIE).; 18th International Conference on Electronics, Information, and Communication, ICEIC 2019 ; Conference date: 22-01-2019 Through 25-01-2019",
year = "2019",
month = may,
day = "3",
doi = "10.23919/ELINFOCOM.2019.8706381",
language = "English",
series = "ICEIC 2019 - International Conference on Electronics, Information, and Communication",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ICEIC 2019 - International Conference on Electronics, Information, and Communication",
}