Adaptive Age Estimation towards Imbalanced Datasets
Source abstract
Abstract
Current age estimation datasets often have a skewed long-tail distribution with significant data imbalance, rather than an ideal uniform distribution for each category. The existing age estimation algorithms that rely on label distribution do not leverage data density information to address the issue of data imbalance. To solve the aforementioned problem, this paper proposes a novel method based on cost-sensitive learning, namely Data-Imbalance Adaptive Age Regression (DIAAR), for age estimation. DIAAR consists of two main modules: the adaptive soft label (ASL) module and the Data Density Smoothing (DDS) module. The ASL module embeds soft labels in the form of probability in the age regression. It assigns different degrees of soft labels adaptively to head and tail data based on their density, which helps balance the dataset. The DDS module further addresses data imbalance by revising data density through kernel smoothing and reweighting the loss function accordingly. Experiments on two benchmark datasets show that DIAAR can effectively deal with data imbalance and improve the accuracy of age estimation, achieving an average improvement of 8% over the baseline models. Moreover, this approach can be applied to various methods based on convolutional neural network models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Imbalanced Data Classification Techniques · Face recognition and analysis · Domain Adaptation and Few-Shot Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Software Technology, Zhejiang University, Ningbo 315048, China
School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
References (48)
Show source-provided references
1. Song, Z., Ni, B., Guo, D., Sim, T., and Yan, S. (2011, January 6–13). Learning universal multi-view age estimator using video context. Proceedings of the International Conference on Computer Vision, Barcelona, Spain.10.1109/ICCV.2011.6126248 ↗
2. Geng, X., Zhou, Z.-H., Zhang, Y., Li, G., and Dai, H. (2006, January 23–27). Learning from facial aging patterns for automatic age estimation. Proceedings of the 14th ACM international Conference on Multimedia, Santa Barbara, CA, USA.10.1145/1180639.1180711 ↗
3. Deep expectation of real and apparent age from a single image without facial landmarks10.1007/s11263-016-0940-3 ↗
4. Comparing different classifiers for automatic age estimation10.1109/TSMCB.2003.817091 ↗
5. A systematic study of the class imbalance problem in convolutional neural networks10.1016/j.neunet.2018.07.011 ↗
6. Ren, M., Zeng, W., Yang, B., and Urtasun, R. (2018, January 10–15). Learning to reweight examples for robust deep learning. Proceedings of the International Conference on Machine Learning, PMLR, Stockholm, Sweden.
7. Geifman, Y., and El-Yaniv, R. (2017). Deep active learning over the long tail. arXiv.
8. Zou, Y., Yu, Z., Kumar, B., and Wang, J. (2018, January 8–14). Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01219-9_18 ↗
9. Ting, K.M. (July, January 29). A comparative study of cost-sensitive boosting algorithms. Proceedings of the 17th International Conference on Machine Learning, Stanford, CA, USA.
10. Training cost-sensitive neural networks with methods addressing the class imbalance problem10.1109/TKDE.2006.17 ↗
11. Huang, C., Li, Y., Loy, C.C., and Tang, X. (2016, January 27–30). Learning deep representation for imbalanced classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.580 ↗
12. Cost-sensitive learning of deep feature representations from imbalanced data10.1109/TNNLS.2017.2732482 ↗
13. Sarafianos, N., Xu, X., and Kakadiaris, I.A. (2018, January 8–14). Deep imbalanced attribute classification using visual attention aggregation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01252-6_42 ↗
14. Cui, Y., Jia, M., Lin, T.Y., Song, Y., and Belongie, S. (2019, January 15–20). Class-balanced loss based on effective number of samples. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00949 ↗
15. Learning to model the tail
16. Distributed representations of words and phrases and their compositionality
17. Mahajan, D., Girshick, R., Ramanathan, V., He, K., Paluri, M., Li, Y., Bharambe, A., and Van Der Maaten, L. (2018, January 8–14). Exploring the limits of weakly supervised pretraining. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01216-8_12 ↗
18. Yang, Y., Zha, K., Chen, Y., Wang, H., and Katabi, D. (2021, January 18–24). Delving into deep imbalanced regression. Proceedings of the International Conference on Machine Learning, PMLR, Virtual Event.
19. Rothe, R., Timofte, R., and Van Gool, L. (2015, January 7–13). Dex: Deep expectation of apparent age from a single image. Proceedings of the IEEE International Conference on Computer Vision Workshop (ICCVW), Santiago, Chile.10.1109/ICCVW.2015.41 ↗
20. 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.
21. Levi, G., and Hassner, T. (2015, January 7–12). Age and gender classification using convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Boston, MA, USA.10.1109/CVPRW.2015.7301352 ↗
22. Huo, Z., Yang, X., Xing, C., Zhou, Y., Hou, P., Lv, J., and Geng, X. (July, January 26). Deep age distribution learning for apparent age estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, USA.
23. Gao, B.-B., Zhou, H.-Y., Wu, J., and Geng, X. (2018, January 13–19). Age Estimation Using Expectation of Label Distribution Learning. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), Stockholm, Sweden.10.24963/ijcai.2018/99 ↗
24. 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 ↗
25. Ordinal deep learning for facial age estimation10.1109/TCSVT.2017.2782709 ↗
26. Liu, X., Zou, Y., Kuang, H., and Ma, X. (2020). Face image age estimation based on data augmentation and lightweight convolutional neural network. Symmetry, 12.10.3390/sym12010146 ↗
27. Yang, T.-S., Huang, Y.-I., Lin, Y.-E., Hsiu, P.-I., and Chuang, Y.-U. (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 ↗
28. Yang, X., Gao, B.-B., Xing, C., Huo, Z.-W., Wei, X.-S., Zhou, Y., Wu, J., and Geng, X. (2015, January 7–13). Deep label distribution learning for apparent age estimation. Proceedings of the IEEE International Conference on Computer Vision Workshop (ICCVW), Santiago, Chile.10.1109/ICCVW.2015.53 ↗
29. 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 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00554 ↗
30. Chang, K.Y., Chen, C.S., and Hung, Y.P. (2010, January 23–26). A ranking approach for human ages estimation based on face images. Proceedings of the 20th International Conference on Pattern Recognition, Istanbul, Turkey.10.1109/ICPR.2010.829 ↗
31. Li, C., Liu, Q., Liu, J., and Lu, H. (2012, January 16–21). Learning ordinal discriminative features for age estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.
32. Chen, S., Zhang, C., Dong, M., Le, J., and Rao, M. (2017, January 21–26). Using ranking-cnn for age estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.86 ↗
33. Age estimation using a hierarchical classifier based on global and local facial features10.1016/j.patcog.2010.12.005 ↗
34. El Dib, M.Y., and El-Saban, M. (2010, January 26–29). Human age estimation using enhanced bio-inspired features (EBIF). Proceedings of the IEEE International Conference on Image Processing, Hong Kong, China.10.1109/ICIP.2010.5651440 ↗
35. 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 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.01287 ↗
36. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
37. Han, H., Wang, W.Y., and Mao, B.H. (2005, January 23–26). Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. Proceedings of the International Conference on Intelligent Computing, Hefei, China.10.1007/11538059_91 ↗
38. Powers, D.M. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv.
39. Fan, W., Stolfo, S.J., Zhang, J., and Chan, P.K. (1999, January 27–30). AdaCost: Misclassification cost-sensitive boosting. Proceedings of the Sixteenth International Conference on Machine Learning, San Francisco, CA, USA.
40. Yang, X., Geng, X., and Zhou, D. (2016, January 9–15). Sparsity Conditional Energy Label Distribution Learning for Age Estimation. Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16), New York, NY, USA.
41. Cao, K., Wei, C., Gaidon, A., Arechiga, N., and Ma, T. (2019, January 8–14). Learning imbalanced datasets with label-distribution-aware margin loss. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada.
42. Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., and Kalantidis, Y. (2019, January 6–9). Decoupling representation and classifier for long-tailed recognition. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA.
43. Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., and Yu, S.X. (2019, January 15–20). Large-scale long-tailed recognition in an open world. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00264 ↗
44. Ren, J., Zhang, M., Yu, C., and Liu, Z. (2022, January 18–24). Balanced MSE for Imbalanced Visual Regression. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00777 ↗
45. Torgo, L., Ribeiro, R.P., Pfahringer, B., and Branco, P. (2013, January 8–11). Smote for regression. Proceedings of the Portuguese Conference on Artificial Intelligence, Coimbra, Portugal.10.1007/978-3-642-40669-0_33 ↗
46. Branco, P., Torgo, L., and Ribeiro, R.P. (2017, January 22). SMOGN: A pre-processing approach for imbalanced regression. Proceedings of the 1st International Workshop on Learning with Imbalanced Domains: Theory and Applications, PMLR, Skopje, Macedonia.
47. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.
48. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv.