Semantic Attention Guided Hierarchical Decision Network for Age Estimation
Source abstract
Abstract
Image-based human age estimation has been a hot topic in the field of face attribute recognition. As the greatest dilemma of age estimation is the similar appearance of adjacent age labels, this paper presents a two-stage age estimation model based on the idea of coarse-to-fine decision strategy and fine-grained feature learning mechanism. In the first stage, Swin Transformer is employed to perform global age estimation for each image, and then an adaptive age range is obtained by local adjusted the global age estimation result. This stage gives a relative age trend of the input image. In the second stage, a local regressor is performed on the generated age range based on a sub-network combining semantic attention mechanism and hierarchical fine-grained feature pooling. The proposed semantic attention provides a guidance of age-sensitive regions for distinguishing fine-grained age-relevant feature in the second stage. The formulation of the proposed two-stage framework is intuitive and end-to-end trainable, and experiments on three popular age estimation benchmarks achieve the state-of-the-art results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Face recognition and analysis · Advanced Neural Network Applications · Domain Adaptation and Few-Shot Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China
Funding
National Natural Science Foundation of China
References (48)
Show source-provided references
1. Rahman, A., Aonty, S.S., Deb, K., and Sarker, I.H. (2023). Attention-Based Human Age Estimation from Face Images to Enhance Public Security. Data, 8.10.3390/data8100145 ↗
2. A Multi-view Mask Contrastive Learning Graph Convolutional Neural Network for Age Estimation10.1007/s10115-024-02193-5 ↗
3. Efficient Group-n Encoding and Decoding for Facial Age Estimation10.1109/TPAMI.2017.2779808 ↗
4. Li, Z., Jiang, R., and Aarabi, P. (2021, January 20–25). Continuous Face Aging via Self-estimated Residual Age Embedding. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01476 ↗
5. Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021, January 10–17). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.10.1109/ICCV48922.2021.00986 ↗
6. Yi, D., Lei, Z., and Li, S.Z. (2014). Age Estimation by Multi-scale Convolutional Network. Computer Vision—ACCV 2014, Proceedings of the 2014 Asian Conference on Computer Vision (ACCV), Singapore, 1–5 November 2014, Springer.
7. Malli, R.C., Aygun, M., and Ekenel, H.K. (July, January 26). Apparent Age Estimation Using Ensemble of Deep Learning Models. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, USA.10.1109/CVPRW.2016.94 ↗
8. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3–7). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Proceedings of the 2021 9th International Conference on Learning Representations (ICLR), Virtually.
9. Chen, P., Zhang, X., Li, Y., Tao, J., Xiao, B., Wang, B., and Jiang, Z. (2023, January 17–24). DAA: A Delta Age AdaIN operation for age estimation via binary code transformer. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.01520 ↗
10. Xu, L., Hu, C., Shu, X., and Yu, H. (2025). Cross spatial and Cross-Scale Swin Transformer for fine-grained age estimation. Comput. Electr. Eng., 123.10.1016/j.compeleceng.2025.110264 ↗
11. He, X., Quan, Y., Xu, R., and Ji, H. (2025, January 11–15). A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts. Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) 2025, Nashville, TN, USA.
12. Wang, X., Zhang, Y., Liu, T., Liu, X., Xu, K., Wan, J., Guo, Y., and Wang, H. (2025, January 11–15). TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression. Proceedings of the 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.
13. Baek, S., Lee, S., Jo, H., Choi, H., and Min, D. (2025). TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning. arXiv.
14. Zhao, Q., Liu, J., and Wei, W. (2024). Mixture of deep networks for facial age estimation. Inf. Sci., 679.10.1016/j.ins.2024.121086 ↗
15. Yang, T.-Y., Huang, Y.-H., Lin, Y.-Y., Hsiu, P.-C., and Chuang, Y.-Y. (2018, January 13–19). SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/150 ↗
16. Bekhouche, S.E., Benlamoudi, A., Dornaika, F., Telli, H., and Bounab, Y. (2024). Facial Age Estimation Using Multi-Stage Deep Neural Networks. Electronics, 13.10.3390/electronics13163259 ↗
17. Li, P., Hu, Y., He, R., and Sun, Z. (2018). A Coupled Evolutionary Network for Age Estimation. arXiv.
18. Zhang, C., Liu, S., Xu, X., and Zhu, C. (2019, January 15–20). C3AE: Exploring the Limits of Compact Model for Age Estimation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.01287 ↗
19. Li, W., Lu, J., Feng, J., Xu, C., Zhou, J., and Tian, Q. (2019, January 15–20). BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00124 ↗
20. GroupFace: Imbalanced Age Estimation Based on Multi-Hop Attention Graph Convolutional Network and Group-Aware Margin Optimization10.1109/TIFS.2024.3520020 ↗
21. Lin, T.-Y., RoyChowdhury, A., and Maji, S. (2015, January 7–13). Bilinear CNN Models for Fine-Grained Visual Recognition. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.170 ↗
22. Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition10.1007/978-3-030-01270-0_35 ↗
23. Salient Object Detection Based on Regional Contrast and Relative Spatial Compactness
24. Three-Dimensional Attention-Based Deep Ranking Model for Video Highlight Detection10.1109/TMM.2018.2815998 ↗
25. Han, K., Guo, J., Zhang, C., and Zhu, M. (2018, January 22–26). Attribute-Aware Attention Model for Fine-grained Representation Learning. Proceedings of the 26th ACM international conference on Multimedia, Seoul, Republic of Korea.10.1145/3240508.3240550 ↗
26. Hu, J., Shen, L., Albanie, S., Sun, G., and Wu, E. (2018, January 18–23). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
27. Fine-Grained Age Estimation in the Wild With Attention LSTM Networks10.1109/TCSVT.2019.2936410 ↗
28. Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion10.1109/TIP.2021.3139226 ↗
29. Fine-Grained Age Estimation With Multi-Attention Network10.1109/ACCESS.2020.3034801 ↗
30. Support vector machine-based optimized decision threshold adjustment strategy for classifying imbalanced data10.1016/j.knosys.2014.12.007 ↗
31. Deep Label Distribution Learning With Label Ambiguity10.1109/TIP.2017.2689998 ↗
32. Rothe, R., Timofte, R., and Gool, L.V. (2015, January 7–13). DEX: Deep EXpectation of Apparent Age from a Single Image. Proceedings of the 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), Santiago, Chile.10.1109/ICCVW.2015.41 ↗
33. Ricanek, K., and Tesafaye, T. (2006, January 10–12). MORPH: A Longitudinal Image Database of Normal Adult Age-Progression. Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition (FGR06), Southampton, UK.
34. Zhang, Y., Liu, L., Li, C., and Loy, C. (2017). change Quantifying Facial Age by Posterior of Age Comparisons. arXiv.10.5244/C.31.108 ↗
35. Face Recognition and Retrieval Using Cross-Age Reference Coding With Cross-Age Celebrity Dataset10.1109/TMM.2015.2420374 ↗
36. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20–25). ImageNet: A Large-Scale Hierarchical Image Database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
37. Pan, H., Han, H., Shan, S., and Chen, X. (2018, January 18–23). Mean-Variance Loss for Deep Age Estimation From a Face. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00554 ↗
38. Facial age estimation based on asymmetrical label distribution10.1007/s00530-022-01022-5 ↗
39. Chen, S., Zhang, C., Dong, M., Le, J., and Rao, M. (2017, January 21–26). Using Ranking-CNN for Age Estimation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.86 ↗
40. Liu, N., Zhang, F., and Duan, F. (2023). Age estimation by extracting hierarchical age-related features. J. Vis. Commun. Image Represent., 95.10.1016/j.jvcir.2023.103884 ↗
41. Deep domain-invariant learning for facial age estimation10.1016/j.neucom.2023.02.037 ↗
42. Wen, C., Zhang, X., Yao, X., and Yang, J. (2023, January 1–6). Ordinal Label Distribution Learning. Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France.10.1109/ICCV51070.2023.02146 ↗
43. Li, P., Hu, Y., Wu, X., He, R., and Sun, Z. (2020). Deep label refinement for age estimation. Pattern Recognit., 100.10.1016/j.patcog.2019.107178 ↗
44. Age Estimation Based on a Single Network with Soft Softmax of Aging Modeling
45. Shen, W., Zhao, K., Guo, Y., and Yuille, A. (2017, January 4–9). Label Distribution Learning Forests. Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA.
46. Auxiliary Demographic Information Assisted Age Estimation With Cascaded Structure10.1109/TCYB.2017.2741998 ↗
47. Li, S., and Cheng, K.T. (2019). Facial Age Estimation by Deep Residual Decision Making. arXiv.
48. Shen, W., Guo, Y., Wang, Y., Zhao, K., Wang, B., and Yuille, A. (2018, January 18–23). Deep Regression Forests for Age Estimation. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00245 ↗