Lightweight Deep Convolutional Network for Tiny Object Recognition

Thanh-Dat Truong, Vinh-Tiep Nguyen, Minh-Triet Tran

Abstract

Object recognition is an important problem in Computer Vision with many applications such as image search, autonomous car, image understanding, etc. In recent years, Convolutional Neural Network (CNN) based models have achieved great success on object recognition, especially VGG, ResNet, Wide ResNet, etc. However, these models involve a large number of parameters that should be trained with large-scale datasets on powerful computing systems. Thus, it is not appropriate to train a heavy CNN with small-scale datasets with only thousands of samples as it is easy to be over-fitted. Furthermore, it is not efficient to use an existing heavy CNN method to recognize small images, such as in CIFAR-10 or CIFAR-100. In this paper, we propose a Lightweight Deep Convolutional Neural Network architecture for tiny images codenamed “DCTI” to reduce significantly a number of parameters for such datasets. Additionally, we use batch-normalization to deal with the change in distribution each layer. To demonstrate the efficiency of the proposed method, we conduct experiments on two popular datasets: CIFAR-10 and CIFAR-100. The results show that the proposed network not only significantly reduces the number of parameters but also improves the performance. The number of parameters in our method is only 21.33% the number of parameters of Wide ResNet but our method achieves up to 94.34% accuracy on CIFAR-10, comparing to 96.11% of Wide ResNet. Besides, our method also achieves the accuracy of 73.65% on CIFAR-100.

References

Download


Paper Citation


in Harvard Style

Truong T., Nguyen V. and Tran M. (2018). Lightweight Deep Convolutional Network for Tiny Object Recognition.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: INDEED, ISBN 978-989-758-276-9, pages 675-682. DOI: 10.5220/0006752006750682


in Bibtex Style

@conference{indeed18,
author={Thanh-Dat Truong and Vinh-Tiep Nguyen and Minh-Triet Tran},
title={Lightweight Deep Convolutional Network for Tiny Object Recognition},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: INDEED,},
year={2018},
pages={675-682},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006752006750682},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: INDEED,
TI - Lightweight Deep Convolutional Network for Tiny Object Recognition
SN - 978-989-758-276-9
AU - Truong T.
AU - Nguyen V.
AU - Tran M.
PY - 2018
SP - 675
EP - 682
DO - 10.5220/0006752006750682