Abstract
In this paper, we present a graph-causal regularization (GCR) for robust facial age estimation. Existing label facial age estimation methods often suffer from overfitting and overconfidence issues due to limited data and domain bias. To address these challenges and leveraging the chronological correlation of age labels, we propose a dynamic graph learning method that enforces causal regularization to discover an attentive feature space while preserving age label dependencies. To mitigate domain bias and enhance aging details, our approach incorporates counterfactual attention and bilateral pooling fusion techniques. Consequently, the proposed GCR achieves reliable feature learning and accurate ordinal decision-making within a globally-tuned framework. Extensive experiments under widely-used protocols demonstrate the superior performance of GCR compared to state-of-the-art approaches.
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
Notes
- 1.
GCR outperformed other methods except for DLDL v2 and AVDL in Morph II setting I. However, they were pretrained on large dataset (i.e. IMDB-WIKI [24]) or private dataset.
References
Ahonen, T., Hadid, A., Pietikäinen, M.: Face description with local binary patterns: application to face recognition. TPAMI 28(12), 2037–2041 (2006)
Bao, Z., Tan, Z., Wan, J., Ma, X., Guo, G., Lei, Z.: Divergence-driven consistency training for semi-supervised facial age estimation. TIFS 18, 221–232 (2022)
Cai, X., Nie, F., et al.: New graph structured sparsity model for multi-label image annotations. In: ICCV, pp. 801–808 (2013)
Dagher, I., Barbara, D.: Facial age estimation using pre-trained cnn and transfer learning. Multimed. Tools. Appl. 80, 20369–20380 (2021)
Deng, Z., et al: PML: progressive margin loss for long-tailed age classification. In: CVPR, pp. 10503–10512 (2021)
Escalera, S., et al.: Chalearn looking at people 2015: apparent age and cultural event recognition datasets and results. In: ICCV Workshops, pp. 243–251 (2015)
Fu, Y., Guo, G., Huang, T.S.: Age synthesis and estimation via faces: a survey. TPAMI 32(11), 1955–1976 (2010)
Gao, B., et al.: Age estimation using expectation of label distribution learning. In: Lang, J. (ed.) IJCAI, pp. 712–718 (2018)
Geng, X., Ji, R.: Label distribution learning. In: ICDM Workshops, pp. 377–383 (2013)
Geng, X., Yin, C., Zhou, Z.: Facial age estimation by learning from label distributions. TPAMI 35(10), 2401–2412 (2013). https://doi.org/10.1109/TPAMI.2013.51
Guo, G., Mu, G., Fu, Y., Huang, T.S.: Human age estimation using bio-inspired features. In: CVPR, pp. 112–119 (2009)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
He, Z., et al.: Data-dependent label distribution learning for age estimation. TIP, pp. 3846–3858 (2017)
Jr., K.R., Tesafaye, T.: MORPH: a longitudinal image database of normal adult age-progression. In: FG, pp. 341–345 (2006)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR. OpenReview.net (2017)
Lanitis, A., Draganova, C., Christodoulou, C.: Comparing different classifiers for automatic age estimation. SMC 34(1), 621–628 (2004)
Li, W., Huang, X., Zhu, Z., Tang, Y., Li, X., Zhou, J., Lu, J.: Ordinalclip: learning rank prompts for language-guided ordinal regression. arXiv preprint arXiv:2206.02338 (2022)
Li, W., Lu, J., Feng, J., Xu, C., Zhou, J., Tian, Q.: Bridgenet: a continuity-aware probabilistic network for age estimation. In: CVPR, pp. 1145–1154 (2019)
Li, W., Lu, J., Wuerkaixi, A., Feng, J., Zhou, J.: Metaage: meta-learning personalized age estimators. TIP 31, 4761–4775 (2022)
Liu, C., Ding, H., Jiang, X.: Gres: generalized referring expression segmentation. In: CVPR, pp. 23592–23601 (2023)
Liu, H., Lu, J., Feng, J., Zhou, J.: Ordinal deep feature learning for facial age estimation. In: FG, pp. 157–164 (2017)
Liu, X., Zou, Y., Kuang, H., Ma, X.: Face image age estimation based on data augmentation and lightweight convolutional neural network. Symmetry 12(1), 146 (2020)
Rao, Y., et al.: Counterfactual attention learning for fine-grained visual categorization and re-identification. In: ICCV, pp. 1005–1014 (2021)
Rothe, R., Timofte, R., Gool, L.V.: DEX: deep expectation of apparent age from a single image. In: ICCV Workshop, pp. 252–257 (2015)
Rothe, R., Timofte, R., Gool, L.V.: Ijcv. Int. J. Comput. Vis. 126(2–4), 144–157 (2018)
Shen, W., Guo, Y., Wang, Y., Zhao, K., Wang, B., Yuille, A.L.: Deep regression forests for age estimation. In: CVPR, pp. 2304–2313 (2018)
Tan, Z., et al.: Efficient group-n encoding and decoding for facial age estimation. TPAMI, pp. 2610–2623 (2018)
Tan, Z., etal.: Deeply-learned hybrid representations for facial age estimation. In: IJCAI, pp. 3548–3554 (2019)
Vermeire, T., Martens, D.: Explainable image classification with evidence counterfactual. CoRR abs/2004.07511 (2020)
Wang, T., Zhou, C., Sun, Q., Zhang, H.: Causal attention for unbiased visual recognition. CoRR abs/2108.08782 (2021)
Wang, X., Saxon, M., Li, J., Zhang, H., Zhang, K., Wang, W.Y.: Causal balancing for domain generalization. arXiv preprint arXiv:2206.05263 (2022)
Woo, S., Park, J., et al.: CBAM: convolutional block attention module. In: ECCV, pp. 3–19 (2018)
Zhang, C., Liu, S., Xu, X., Zhu, C.: C3AE: exploring the limits of compact model for age estimation. In: CVPR, pp. 12587–12596 (2019)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Zhang, Y., Liu, L., et al.: Quantifying facial age by posterior of age comparisons. In: BMVC (2017)
Zhang, Z., Song, Y., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: CVPR, pp. 4352–4360 (2017)
Acknowledgment
This work was supported in part by the National Science Foundation of China under Grants 62076142 and 62241603, in part by the National Key Research and Development Program of Ningxia under Grant 2023AAC05009, 2022BEG03158 and 2021BEB0406.
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
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, T., Dong, X., Li, Z., Liu, H. (2024). Co-regularized Facial Age Estimation with Graph-Causal Learning. In: Liu, Q., et al. Pattern Recognition and Computer Vision. PRCV 2023. Lecture Notes in Computer Science, vol 14432. Springer, Singapore. https://doi.org/10.1007/978-981-99-8543-2_13
Download citation
DOI: https://doi.org/10.1007/978-981-99-8543-2_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8542-5
Online ISBN: 978-981-99-8543-2
eBook Packages: Computer ScienceComputer Science (R0)