Abstract
Recent deep learning based Rotation-Invariant Face Detection (RIFD) algorithms make efforts to explore a mapping function from face appearance to the rotation-in-plane (RIP) orientation. Most methods propose to predict RIP angles in a coarse-to-fine cascade regression style and improve the overall RIFD performance. However, the problem of suboptimal between the models of training phase and testing phase cannot be solved because of its cascaded nature. The weakness of ambiguous mapping between face appearance and its real orientation would also degrade the performance considerably. In this paper, we propose a novel Direction-Sensitivity Features Ensemble Network for rotation-invariant face detection (DFE-Net) which learns an end-to-end convolutional model for RIFD from coarse to fine. Specifically, the incline bounding box regression is implemented by introducing angle prediction based on improved SSD. A Direction-Sensitivity Features Ensemble Module (DFEM) is adopted in the network to progressively focus on the awareness of face angle information, which can learn and accurately extract features of rotated regions and locate rotated faces precisely. Finally, we add multi-task loss to guide the learning process to captures consistent face appearance-orientation relationships. Extensive experiments on two challenging benchmarks demonstrate that the proposed framework achieves favorable performance and consistently outperforms the state-of-the-art algorithms.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Zhou, L., Du, Y., Li, W., et al.: Pose-robust face recognition with Huffman-LBP enhanced by divide-and-rule strategy. Pattern Recogn. 78, 43–55 (2018)
Thies, J., Zollhofer, M., Stamminger, M., et al.: Face2face: real-time face capture and reenactment of RGB videos. In: CVPR, pp. 2387–2395. IEEE Press, Las Vegas (2016)
Ranjan, R., Patel, V.M., Chellappa, R.: HyperFace: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 121–135 (2016)
Shi, X., Shan, S., Kan, M., et al.: Real-time rotation-invariant face detection with progressive calibration networks. In: CVPR, pp. 2295–2303. IEEE Press, Salt Lake City (2018)
Rowley, H.A., Baluja, S., Kanade, T.: Rotation invariant neural network-based face detection. In: CVPR, pp. 38–44. IEEE Press, Santa Barbara (1998)
Huang, C., Ai, H., Li, Y., et al.: High-performance rotation invariant multiview face detection. IEEE Trans. Pattern Anal. Mach. Intell. 29(4), 671–686 (2007)
Zhang, K., Zhang, Z., Li, Z., et al.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Yang, B., Yang, C., Liu, Q., et al.: Joint rotation-invariance face detection and alignment with angle-sensitivity cascaded networks. In: ACM’ MM, pp. 1473–1480. ACM Press, Istanbul (2019)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Farfade, S.S., Saberian, M.J., Li, L.: Multi-view face detection using deep convolutional neural networks. In: ICMR, pp. 643–650. ACM Press, New York (2015)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: CVPR, pp. 2879–2886. IEEE Press, Providence (2012)
Jain, V., Learned-Miller, E.: FDDB: a benchmark for face detection in unconstrained settings. UMass Amherst Technical report (2010)
Jaderberg, M., Simonyan, K., Zisserman, A.: Spatial transformer networks. In: NIPS, pp. 2017–2025. MIT Press, Montreal (2015)
Lin, T., Dollár, P., Girshick, R., et al.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125. IEEE Press, Honolulu (2017)
Chen, D., Hua, G., Wen, F., Sun, J.: Supervised transformer network for efficient face detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 122–138. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46454-1_8
Liu, Y., Shen, Z., Lin, Z., et al,: GIFT: learning transformation-invariant dense visual descriptors via group CNNs. In: NIPS, pp. 6992–7003. MIT Press, Vancouver (2019)
Marcos, D., Volpi, M., Tuia, D.: Learning rotation invariant convolutional filters for texture classification. In: ICPR, pp. 2012–2017. IEEE Press (2016)
Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91–99. MIT Press, Montreal (2015)
Li, H., Lin, Z., Shen, X., et al.: A convolutional neural network cascade for face detection. In: CVPR, pp. 5325–5334. IEEE Press, Boston (2015)
Yang, S., Luo, P., Loy, C., et al.: Wider face: a face detection benchmark. In: CVPR, pp. 5525–5533. IEEE Press, Las Vegas (2016)
Acknowledgment
This work was supported by the Science and Technology Research Program of Chongqing Municipal Education Commission (Grant No. KJZD-K201900601) and by the National Natural Science Foundation of Chongqing (Grant No. cstc2019jcyj-msxmX0461).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, LF., Gu, Y., Liang, S., Lei, BJ., Liu, J. (2020). Direction-Sensitivity Features Ensemble Network for Rotation-Invariant Face Detection. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12306. Springer, Cham. https://doi.org/10.1007/978-3-030-60639-8_48
Download citation
DOI: https://doi.org/10.1007/978-3-030-60639-8_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60638-1
Online ISBN: 978-3-030-60639-8
eBook Packages: Computer ScienceComputer Science (R0)