Abstract
We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which is valuable for many applications. This is a classical multi-task learning problem. However, no dataset exists that these tasks could be jointly learned from. Hence several datasets need to be combined during training, which in other contexts has often led to reduced performance in the past. We extensively evaluate how the different task and datasets influence each other and how different degrees of parameter sharing between the tasks affect performance. Our final model matches or outperforms its single-task counterparts without creating significant computational overhead, rendering it highly interesting for resource-constrained scenarios such as mobile robotics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Uncertainty weighting by Kendall et al. [12] gave no consistent improvements.
References
Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR (2014)
Bai, S., Bai, X., Tian, Q.: Scalable person re-identification on supervised smoothed manifold. In: CVPR (2017)
Caruana, R.: Multitask learning: a knowledge-based source of inductive bias. In: ICML (1993)
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. PAMI 40(4), 834–848 (2018)
Fu, C.Y.: Pytorch-groupnormalization. https://github.com/chengyangfu/pytorch-groupnormalization (2018). Accessed 08 Feb 2019
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: CVPR (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hermans, A., Beyer, L., Leibe, B. In defense of the triplet loss for person re-identification. arXiv:1703.07737 (2017)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
Jin, X., Lan, C., Zeng, W., Zhang, Z., Chen, Z.: CaseNet: content-adaptive scale interaction networks for scene parsing. arXiv:1904.08170 (2019)
Kalayeh, M.M., Basaran, E., Gökmen, M., Kamasak, M.E., Shah, M.: Human semantic parsing for person re-identification. In: CVPR (2018)
Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Kirillov, A., Girshick, R., He, K., Dollár, P.: Panoptic feature pyramid networks. arXiv:1901.02446 (2019)
Kokkinos, I.: Ubernet: training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory. In: CVPR (2017)
Liang, X., Gong, K., Shen, X., Lin, L.: Look into person: joint body parsing & pose estimation network and a new benchmark. PAMI 41(4), 871–885 (2018)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)
Lin, Y., Zheng, L., Zheng, Z., Wu, Y., Yang, Y.: Improving person re-identification by attribute and identity learning. arXiv:1703.07220 (2017)
Liu, H., Wu, J., Jiang, J., Qi, M., Bo, R.: Sequence-based person attribute recognition with joint CTC-attention model. W:1811.08115 (2018)
Luo, H., Gu, Y., Liao, X., Lai, S., Jiang, W.: Bag of tricks and a strong baseline for deep person re-identification. In: CVPR Workshops (2019)
Luvizon, D.C., Picard, D., Tabia, H.: 2D/3D pose estimation and action recognition using multitask deep learning. In: CVPR (2018)
Milan, A., Leal-Taixé, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv:1603.00831 (2016)
Papandreou, G., Zhu, T., Chen, L.-C., Gidaris, S., Tompson, J., Murphy, K.: PersonLab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 282–299. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_17
Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS Autodiff Workshop (2017)
Qian, X., et al.: Pose-normalized image generation for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 661–678. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01240-3_40
Quispe, R., Pedrini, H.: Improved person re-identification based on saliency and semantic parsing with deep neural network models. arXiv:1807.05618 (2018)
Ranjan, R., Patel, V.M., Chellappa, R.: HyperFace: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. PAMI 41(1), 121–135 (2019)
Rebuffi, S.A., Bilen, H., Vedaldi, A.: Learning multiple visual domains with residual adapters. In: NIPS (2017)
Ruan, T., et al.: Devil in the details: towards accurate single and multiple human parsing. In: AAAI (2019)
Ruder, S.: An overview of multi-task learning in deep neural networks. arXiv:1706.05098 (2017)
Saquib Sarfraz, M., Schumann, A., Eberle, A., Stiefelhagen, R.: A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. In: CVPR (2018)
Sárándi, I., Linder, T., Arras, K.O., Leibe, B.: Synthetic occlusion augmentation with volumetric heatmaps for the 2018 ECCV PoseTrack challenge on 3D human pose estimation. arXiv:1809.04987 (2018)
Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K.M.: Part-aligned bilinear representations for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision – ECCV 2018. LNCS, vol. 11218, pp. 418–437. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01264-9_25
Sun, C., Jiang, N., Zhang, L., Wang, Y., Wu, W., Zhou, Z.: Unified framework for joint attribute classification and person re-identification. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 637–647. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_63
Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 536–553. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_33
Tang, W., Yu, P., Wu, Y.: Deeply learned compositional models for human pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 197–214. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_12
Tompson, J., Goroshin, R., Jain, A., LeCun, Y., Bregler, C.: Efficient object localization using convolutional networks. In: CVPR (2015)
Wang, C., Zhang, Q., Huang, C., Liu, W., Wang, X.: Mancs: a multi-task attentional network with curriculum sampling for person re-identification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 384–400. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_23
Wang, G., Yuan, Y., Chen, X., Li, J., Zhou, X.: learning discriminative features with multiple granularities for person re-identification. In: ACM MM (2018)
Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_1
Wu, Z., Shen, C., v. d. Hengel, A.: Bridging category-level and instance-level semantic image segmentation. arXiv:1605.06885 (2016)
Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432–448. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_26
Xiao, T., Li, S., Wang, B., Lin, L., Wang, X.: Joint detection and identification feature learning for person search. In: CVPR (2017)
Yang, W., Li, S., Ouyang, W., Li, H., Wang, X.: Learning feature pyramids for human pose estimation. In: ICCV (2017)
Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: CVPR (2018)
Zheng, F., et al.: Pyramidal person re-identification via multi-loss dynamic training (2019)
Acknowledgements
This project was funded, in parts, by ERC Consolidator Grant project “DeeViSe” (ERC-CoG-2017-773161) and the BMBF projects “FRAME” (16SV7830) and “PARIS” (16ES0602). Istvan Sarandi’s research is funded by a grant from the Bosch Research Foundation. Most experiments were performed on the RWTH Aachen University CLAIX 2018 GPU Cluster.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Pfeiffer, K., Hermans, A., Sárándi, I., Weber, M., Leibe, B. (2019). Visual Person Understanding Through Multi-task and Multi-dataset Learning. In: Fink, G., Frintrop, S., Jiang, X. (eds) Pattern Recognition. DAGM GCPR 2019. Lecture Notes in Computer Science(), vol 11824. Springer, Cham. https://doi.org/10.1007/978-3-030-33676-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-33676-9_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33675-2
Online ISBN: 978-3-030-33676-9
eBook Packages: Computer ScienceComputer Science (R0)