Abstract
In recent years, the performance of object detection algorithm has been improved continuously, and it has become an important direction in the field of computer vision. All the work in this paper will be based on a two-stage object detection algorithm. First, the dilated convolution network is added to the backbone network to form the Deep_Dilated Convolution Network (D_dNet), which improves the resolution of the feature map and the size of the receptive field. In addition, in order to obtain higher accuracy, the feature map of pretraining is compressed and a light-weight network is established. Finally, to further optimize the proposed two network models, this paper introduces the transfer learning into the pretraining. The whole experiment is evaluated based on MSCOCO dataset. Experiments show that the accuracy of the proposed model is improved by 1.3 to 2.2% points.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anderson, P., He, X., Buehler, C., et al.: Bottom-up and top-down attention for image captioning and visual question answering, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6077–6086 (2018)
Chen, X., Fang, H., Lin, T.Y., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)
Dai, J., Li, Y., He, K., et al.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 379–387 (2016)
Deng, Z., Li, K., Zhao, Q., et al.: Effective face landmark localization via single deep network. arXiv preprint arXiv:1702.02719 (2017)
Erhan, D., Szegedy, C., Toshev, A., et al.: Scalable object detection using deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2147–2154 (2014)
Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587 (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
He, K., Gkioxari, G., Dollár, P., et al.: Mask R-CNN. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988 (2017)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 1097–1105 (2012)
Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Lin, T.Y., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117–2125 (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440 (2015)
Li, Z., Peng, C., Yu, G., et al.: DetNet: a backbone network for object detection. arXiv preprint arXiv:1804.06215 (2018)
Li, Z., Peng, C., Yu, G., et al.: Light-head R-CNN: in defense of two-stage object detector. arXiv preprint arXiv:1711.07264 (2017)
Oquab, M., Bottou, L., Laptev, I., et al.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1717–1724 (2014)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Steder, B., Rusu, R.B., Konolige, K., et al.: Point feature extraction on 3D range scans taking into account object boundaries. In: 2011 IEEE International Conference on Robotics and Automation, pp. 2601–2608. IEEE (2011)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Shrivastava, A., Sukthankar, R., Malik, J., et al.: Beyond skip connections: top-down modulation for object detection. arXiv preprint arXiv:1612.06851 (2016)
Vinyals, O., Toshev, A., Bengio, S., et al.: Show and tell: lessons learned from the 2015 mscoco image captioning challenge. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 652–663 (2017)
Wagner, R., Thom, M., Schweiger, R., et al.: Learning convolutional neural networks from few samples. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2013)
Yongzhe, Z., Zhixin, L., Canlong, Z.: A hybrid architecture based on CNN for cross-modal semantic instance annotation. Multimedia Tools Appl. 77(7), 8695–8710 (2018)
Acknowledgments
This work is supported by the National Natural Science Foundation of China (Nos. 61663004, 61762078, 61866004), the Guangxi Natural Science Foundation (Nos. 2016GXNSFAA380146, 2017GXNSFAA198365, 2018GXNSFDA281009), the Research Fund of Guangxi Key Lab of Multi-source Information Mining and Security (16-A-03-02, MIMS18-08), the Guangxi Special Project of Science and Technology Base and Talents (AD16380008), Innovation Project of Guangxi Graduate Education (XYCSZ2019068) and the Guangxi “Bagui Scholar” Teams for Innovation and Research Project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Quan, Y., Li, Z., Zhang, C. (2019). Object Detection by Combining Deep Dilated Convolutions Network and Light-Weight Network. In: Douligeris, C., Karagiannis, D., Apostolou, D. (eds) Knowledge Science, Engineering and Management. KSEM 2019. Lecture Notes in Computer Science(), vol 11775. Springer, Cham. https://doi.org/10.1007/978-3-030-29551-6_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-29551-6_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-29550-9
Online ISBN: 978-3-030-29551-6
eBook Packages: Computer ScienceComputer Science (R0)