Abstract
Abstract
Most of the recent successful object detection methods have been based on convolutional neural networks (CNNs). From previous studies, we learned that many feature reuse methods improve the network performance, but they increase the number of parameters. DenseNet uses thin layers that have fewer channels to alleviate the increase in parameters. This motivated us to find other methods for solving the increase in model size problems introduced by feature reuse methods. In this work, we employ different feature reuse methods on fire units and mobile units. We solved the problem and constructed two novel neural networks, fire-FRD-CNN and mobile-FRD-CNN. We conducted experiments with the proposed neural networks on KITTI and PASCAL VOC datasets.
Publisher
Springer Science and Business Media LLC
Reference24 articles.
1. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 770–778 (2015).
2. Huang, G., Liu, Z., Laurens, V. D. M. & Weinberger, K. Q. Densely Connected Convolutional Networks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 4700–4708 (2017).
3. Geiger, A., Lenz, P. & Urtasun R. Are we ready for autonomous driving? the kitti vision benchmark suite. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 3354–3361 (2012).
4. Everingham, M. & Winn, J. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Development Kit. International Journal of Computer Vision. 1, 98–136 (2006).
5. Cai, Z., Fan, Q., Feris, R. S. & Vasconcelos, N. A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection. European Conference on Computer Vision. 354–370 (2016).
Cited by
14 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献