Abstract
The existing human pose estimation (HPE) models show good performance, but also reflect a pair of contradictions between the computational complexity and prediction performance. To address this dilemma, this paper proposes a novel HPE training approach via self-guided learning (SGL). Specifically, a dual model training is designed to get the model-temporal ensemble learning to fuse the knowledge from a new guidance model. Moreover, a self-guided joint loss is considered with the key-point attention enhancement and self-guided compensation. Experimental results show that the proposed SGL method not only has a lower computation cost, but also achieves a higher prediction precision.
This work was supported in part by Natural Science Foundation of Guangdong Province (No. 2019A1515010961 and No. 2021A1515011877), and in part by Natural Science Foundation of Shenzhen City (No. 2021A1515011877 and No. JCYJ20180305124209486).
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
Alp Güler, R., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7297–7306 (2018)
Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7103–7112 (2018)
Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. arXiv preprint arXiv:2006.05525 (2020)
Groos, D., Ramampiaro, H., Ihlen, E.: Efficientpose: scalable single-person pose estimation. arXiv preprint arXiv:2004.12186 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)
Iandola, F., Moskewicz, M., Karayev, S., Girshick, R., Darrell, T., Keutzer, K.: Densenet: implementing efficient convnet descriptor pyramids. arXiv preprint arXiv:1404.1869 (2014)
Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2704–2713 (2018)
Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2020)
Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242 (2016)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Radosavovic, I., Dollár, P., Girshick, R., Gkioxari, G., He, K.: Data distillation: Towards omni-supervised learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4119–4128 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Neural Information Processing Systems (NIPS) (2017)
Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020)
Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724–4732 (2016)
Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: European Conference on Computer Vision (ECCV), September 2018
Xu, X., Zou, Q., Lin, X., Huang, Y., Tian, Y.: Integral knowledge distillation for multi-person pose estimation. IEEE Signal Process. Lett. 27, 436–440 (2020)
Yang, Y., Qiu, J., Song, M., Tao, D., Wang, X.: Distilling knowledge from graph convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7074–7083 (2020)
Zhang, F., Zhu, X., Ye, M.: Fast human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, Z., Wang, M. (2021). Deep Human Pose Estimation via Self-guided Learning. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12889. Springer, Cham. https://doi.org/10.1007/978-3-030-87358-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-87358-5_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87357-8
Online ISBN: 978-3-030-87358-5
eBook Packages: Computer ScienceComputer Science (R0)