Deep learning methods are powerful approaches but often require expensive computations and lead to models of high complexity which need to be trained with large amounts of data. In this paper, we consider the problem of face detection and we propose a light-weight deep convolutional neural network that achieves a state-of-the-art recall rate of 90% at the challenging FDDB dataset. Our model is designed with a view to minimize both training and run time and outperforms the convolutional network used in [2] for the same task. Our model consists of only 76.554 free parameters whereas the previously proposed CNN for face detection had 60 million parameters. Our model also requires 250 times fewer floating point operations than AlexNet. We propose a new training method that gradually increases the difficulty of both negative and positive examples and has proved to drastically improve training speed and accuracy. The proposed method is able to detect faces under severe occlusion and unconstrained pose variation and meets the difficulties and the large variations of real-world face detection.
CITATION STYLE
Triantafyllidou, D., & Tefas, A. (2017). A fast deep convolutional neural network for face detection in big visual data. In Advances in Intelligent Systems and Computing (Vol. 529, pp. 61–70). Springer Verlag. https://doi.org/10.1007/978-3-319-47898-2_7
Mendeley helps you to discover research relevant for your work.