Abstract
Existing lightweight networks perform inferior to large-scale models in human pose estimation because of shallow model depths and limited receptive fields. Current approaches utilize large convolution kernels or attention mechanisms to encourage long-range receptive field learning at the expense of model redundancy. In this paper, we propose a novel Multi-scale Field Lightweight High-resolution Network (MFite-HRNet) for human pose estimation. Specifically, our model mainly consists of two lightweight blocks, a Multi-scale Receptive Field Block (MRB) and a Large Receptive Field Block (LRB), to learn informative multi-scale and long-range spatial context information. The MRB utilizes group depthwise dilation convolutions with varied dilation rates to extract multi-scale spatial relationships from different feature maps. The LRB leverages large depthwise convolution kernels to model large-range spatial knowledge at the low-level features. We apply MFite-HRNet to single-person and multi-person pose estimation tasks. Experiments on COCO, MPII, and CrowdPose datasets demonstrate that our network outperforms current state-of-the-art lightweight networks in either single-person or multi-person pose estimation tasks. The source code will be publicly available at https://github.com/lskdje/MFite-HRNet.git.
Similar content being viewed by others
Data Availability
Data are available on reasonable request from the corresponding author.
Notes
Small HRNet is available at https://github.com/HRNet/HRNet-Semantic-Segmentation. It simply reduces the depths and widths of the original HRNet.
References
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: ECCV, pp. 483–499 (2016)
Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: CVPR, pp. 7103–7112 (2018)
Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR, pp. 5693–5703 (2019)
Wang, C.-H., Huang, K.-Y., Yao, Y., Chen, J.-C., Shuai, H.-H., Cheng, W.-H.: Lightweight deep learning: an overview. IEEE CONSUM ELECTR M, 1–12 (2022) https://doi.org/10.1109/MCE.2022.3181759
Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv PrePrint: arXiv:1704.04861 (2017)
Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: CVPR, pp. 6848–6856 (2018)
Yu, C., Xiao, B., Gao, C., Yuan, L., Zhang, L., Sang, N., Wang, J.: Lite-hrnet: A lightweight high-resolution network. In: CVPR, pp. 10440–10450 (2021)
Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: ECCV, pp. 116–131 (2018)
Li, Q., Zhang, Z., Xiao, F., Zhang, F., Bhanu, B.: Dite-hrnet: Dynamic lightweight high-resolution network for human pose estimation. In: IJCAI, pp. 1095–1101 (2022)
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: ECCV, pp. 740–755 (2014)
Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: New benchmark and state of the art analysis. In: CVPR, pp. 3686–3693 (2014)
Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.-S., Lu, C.: Crowdpose: Efficient crowded scenes pose estimation and a new benchmark. In: CVPR, pp. 10863–10872 (2019)
Wei, S.-E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: CVPR, pp. 4724–4732 (2016)
Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: ECCV, pp. 466–481 (2018)
Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: ECCV, pp. 529–545 (2018)
Fang, H.-S., Xie, S., Tai, Y.-W., Lu, C.: Rmpe: Regional multi-person pose estimation. In: ICCV, pp. 2334–2343 (2017)
Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. In: CVPR, pp. 5386–5395 (2020)
Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: Bottom-up human pose estimation via disentangled keypoint regression. In: CVPR, pp. 14676–14686 (2021)
Jin, S., Liu, W., Xie, E., Wang, W., Qian, C., Ouyang, W., Luo, P.: Differentiable hierarchical graph grouping for multi-person pose estimation. In: ECCV, pp. 718–734 (2020)
Kreiss, S., Bertoni, L., Alahi, A.: Pifpaf: Composite fields for human pose estimation. In: CVPR, pp. 11977–11986 (2019)
Kendall, A., Grimes, M., Cipolla, R.: Posenet: A convolutional network for real-time 6-dof camera relocalization. In: ICCV, pp. 2938–2946 (2015)
Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: CVPR, pp. 7291–7299 (2017)
Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: Deepercut: A deeper, stronger, and faster multi-person pose estimation model. In: ECCV, pp. 34–50 (2016)
Newell, A., Huang, Z., Deng, J.: Associative embedding: End-to-end learning for joint detection and grouping. In: NeurIPS, pp. 2277–2287 (2017)
Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.: Mobilenetv2: Inverted residuals and linear bottlenecks. In: CVPR, pp. 4510–4520 (2018)
Howard, A., Pang, R., Adam, H., Le, Q.V., Sandler, M., Chen, B., Wang, W., Chen, L., Tan, M., Chu, G., Vasudevan, V., Zhu, Y.: Searching for mobilenetv3. In: ICCV, pp. 1314–1324 (2019)
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. TPAMI 40(4), 834–848 (2017)
Neff, C., Sheth, A., Furgurson, S., Tabkhi, H.: Efficienthrnet: Efficient scaling for lightweight high-resolution multi-person pose estimation. arXiv preprint arXiv:2012.14214 (2020)
Wang, Y., Li, M., Cai, H., Chen, W.-M., Han, S.: Lite pose: Efficient architecture design for 2d human pose estimation. In: CVPR, pp. 13126–13136 (2022)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Contributors, M.: OpenMMLab pose estimation toolbox and benchmark. https://github.com/open-mmlab/mmpose (2020)
Huang, J., Zhu, Z., Guo, F., Huang, G.: The devil is in the details: delving into unbiased data processing for human pose estimation. In: CVPR, pp. 5700–5709 (2020)
Cai, H., Chen, T., Zhang, W., Yu, Y., Wang, J.: Efficient architecture search by network transformation. In: AAAI, vol. 32 (2018)
Acknowledgements
This research is supported by National Key R\( { \& }\)D Program of China (No. 2022ZD0115902) and National Natural Science Foundation of China (Nos. 62102208, 62272017, U20A20195, 62172437).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, S., Dai, J., Chen, Z. et al. A lightweight pose estimation network with multi-scale receptive field. Vis Comput 39, 3429–3440 (2023). https://doi.org/10.1007/s00371-023-02953-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-023-02953-4