Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Hierarchical Attention-based Age Estimation and Bias Estimation (2103.09882v2)

Published 17 Mar 2021 in cs.CV

Abstract: In this work we propose a novel deep-learning approach for age estimation based on face images. We first introduce a dual image augmentation-aggregation approach based on attention. This allows the network to jointly utilize multiple face image augmentations whose embeddings are aggregated by a Transformer-Encoder. The resulting aggregated embedding is shown to better encode the face image attributes. We then propose a probabilistic hierarchical regression framework that combines a discrete probabilistic estimate of age labels, with a corresponding ensemble of regressors. Each regressor is particularly adapted and trained to refine the probabilistic estimate over a range of ages. Our scheme is shown to outperform contemporary schemes and provide a new state-of-the-art age estimation accuracy, when applied to the MORPH II dataset for age estimation. Last, we introduce a bias analysis of state-of-the-art age estimation results.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. A. Hakeem, H. Gupta, A. Kanaujia, T. E. Choe, K. Gunda, A. W. Scanlon, L. Yu, Z. Zhang, P. L. Venetianer, Z. Rasheed, and N. Haering, “Video analytics for business intelligence,” in Video Analytics for Business Intelligence, 2012.
  2. A. Lanitis, C. Draganova, and C. Christodoulou, “Comparing different classifiers for automatic age estimation,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 34, pp. 621–628, 2004.
  3. V. Lambros, “Facial aging: A 54-year, three-dimensional population study,” Plastic and reconstructive surgery, vol. 145, pp. 921–928, 04 2020.
  4. E. Eidinger, R. Enbar, and T. Hassner, “Age and gender estimation of unfiltered faces,” IEEE Transactions on Information Forensics and Security, vol. 9, no. 12, pp. 2170–2179, 2014.
  5. G. Guo and G. Mu, “Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2011, pp. 657–664.
  6. K.-Y. Chang, C.-S. Chen, and Y.-P. Hung, “Ordinal hyperplanes ranker with cost sensitivities for age estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2011, pp. 585–592.
  7. D. Cao, Z. Lei, Z. Zhang, J. Feng, and S. Z. Li, “Human age estimation using ranking svm,” in Biometric Recognition, W.-S. Zheng, Z. Sun, Y. Wang, X. Chen, P. C. Yuen, and J. Lai, Eds.   Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 324–331.
  8. E. Ramón-Balmaseda, J. Lorenzo-Navarro, and M. Castrillón-Santana, “Gender classification in large databases,” in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications.   Springer, 2012, pp. 74–81.
  9. G. Guo and G. Mu, “Human age estimation: What is the influence across race and gender?” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2010, pp. 71–78.
  10. X. Wang and C. Kambhamettu, “Age estimation via unsupervised neural networks,” in International Conference on Automatic Face and Gesture Recognition (FGR), vol. 1, May 2015, pp. 1–6.
  11. K. Chen, S. Gong, T. Xiang, and C. Loy, “Cumulative attribute space for age and crowd density estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2013, pp. 2467–2474.
  12. G. Levi and T. Hassner, “Age and gender classification using convolutional neural networks,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2015, pp. 34–42.
  13. J. Deng, J. Guo, E. Ververas, I. Kotsia, and S. Zafeiriou, “Retinaface: Single-shot multi-level face localisation in the wild,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).   IEEE, 2020, pp. 5202–5211.
  14. H. Liu, J. Lu, J. Feng, and J. Zhou, “Label-sensitive deep metric learning for facial age estimation,” IEEE Transactions on Information Forensics and Security, vol. 13, no. 2, pp. 292–305, 2018.
  15. O. Sendik and Y. Keller, “Deepage: Deep learning of face-based age estimation,” Signal Processing: Image Communication, vol. 78, 08 2019.
  16. R. Hadsell, S. Chopra, and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, 2006, pp. 1735–1742.
  17. K. Li, J. Xing, C. Su, W. Hu, Y. Zhang, and S. Maybank, “Deep cost-sensitive and order-preserving feature learning for cross-population age estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 399–408.
  18. Q. Tian, M. Cao, S. Chen, and H. Yin, “Relationships self-learning based gender-aware age estimation,” Neural Processing Letters, vol. 50, no. 3, pp. 2141–2160, 2019.
  19. S. Chen, C. Zhang, M. Dong, J. Le, and M. Rao, “Using ranking-cnn for age estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 742–751.
  20. Z. Niu, M. Zhou, L. Wang, X. Gao, and G. Hua, “Ordinal regression with multiple output cnn for age estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 4920–4928.
  21. X. Zeng, J. Huang, and C. Ding, “Soft-ranking label encoding for robust facial age estimation,” IEEE Access, vol. 8, pp. 134 209–134 218, 2020.
  22. Q. Zhao, J. Dong, H. Yu, and S. Chen, “Distilling ordinal relation and dark knowledge for facial age estimation,” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, 07 2020.
  23. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in NAACL-HLT.   Minneapolis, Minnesota: Association for Computational Linguistics, Jun. 2019, pp. 4171–4186.
  24. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems (NIPS), I. Guyon, U. von Luxburg, S. Bengio, H. M. Wallach, R. Fergus, S. V. N. Vishwanathan, and R. Garnett, Eds., 2017, pp. 5998–6008.
  25. I. Kim, Y. Kim, and S. Kim, “Learning loss for test-time augmentation,” in Advances in Neural Information Processing Systems (NIPS).   Curran Associates Inc., 2020.
  26. W. Cao, V. Mirjalili, and S. Raschka, “Rank consistent ordinal regression for neural networks with application to age estimation,” Pattern Recognition Letters, vol. 140, pp. 325–331, 2020.
  27. W. Li, J. Lu, J. Feng, C. Xu, J. Zhou, and Q. Tian, “Bridgenet: A continuity-aware probabilistic network for age estimation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 1145–1154.
  28. J. G. Cavazos, P. J. Phillips, C. D. Castillo, and A. J. O’Toole, “Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?” IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 3, no. 1, pp. 101–111, 2021.
  29. J. Buolamwini and T. Gebru, “Gender shades: Intersectional accuracy disparities in commercial gender classification,” in Proceedings of the 1st Conference on Fairness, Accountability and Transparency, S. A. Friedler and C. Wilson, Eds., vol. 81, 2018, pp. 77–91.
  30. P. Drozdowski, C. Rathgeb, A. Dantcheva, N. Damer, and C. Busch, “Demographic bias in biometrics: A survey on an emerging challenge,” IEEE Transactions on Technology and Society, vol. 1, no. 2, pp. 89–103, 2020.
  31. J. P. Robinson, G. Livitz, Y. Henon, C. Qin, Y. Fu, and S. Timoner, “Face recognition: too bias, or not too bias?” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020, pp. 0–10.
  32. A. Das, A. Dantcheva, and F. Bremond, “Mitigating bias in gender, age and ethnicity classification: A multi-task convolution neural network approach,” in European Conference on Computer Vision Workshops (ECCVW), 2018, pp. 573–585.
  33. A. Clapés, G. Anbarjafari, O. Bilici, D. Temirova, E. Avots, and S. Escalera, “From apparent to real age: Gender, age, ethnic, makeup, and expression bias analysis in real age estimation,” in IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2018, pp. 2436–243 609.
  34. J. P. Robinson, C. Qin, Y. Henon, S. Timoner, and Y. Fu, “Balancing biases and preserving privacy on balanced faces in the wild,” arXiv preprint arXiv:2103.09118, 2021.
  35. K. Ricanek and T. Tesafaye, “Morph: a longitudinal image database of normal adult age-progression,” in International Conference on Automatic Face and Gesture Recognition (FGR), 2006, pp. 341–345.
  36. B.-C. Chen, C.-S. Chen, and W. H. Hsu, “Cross-age reference coding for age-invariant face recognition and retrieval,” in Proceedings of the European Conference on Computer Vision (ECCV), 2014, pp. 768–783.
  37. H. Han, C. Otto, X. Liu, and A. K. Jain, “Demographic estimation from face images: Human vs. machine performance,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 6, pp. 1148–1161, 2015.
  38. R. Rothe, R. Timofte, and L. Van Gool, “Dex: Deep expectation of apparent age from a single image,” in Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), 2015, pp. 252–257.
  39. H. Pan, H. Han, S. Shan, and X. Chen, “Mean-variance loss for deep age estimation from a face,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).   IEEE Computer Society, 2018, pp. 5285–5294.
  40. R. C. Malli, M. Aygun, and H. K. Ekenel, “Apparent age estimation using ensemble of deep learning models,” 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 714–721, Jun 2016.
  41. W. Shen, Y. Guo, Y. Wang, K. Zhao, B. Wang, and A. Yuille, “Deep regression forests for age estimation,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 2304–2313.
  42. T. Cootes and A. Lanitis, “The fg-net aging database,” 2002, available online at http://www-prima.inrialpes.fr/FGnet/.
  43. P. Phillips, H. Wechsler, J. Huang, and P. J. Rauss, “The FERET database and evaluation procedure for face-recognition algorithms,” Image and Vision Computing, vol. 16, no. 5, pp. 295–306, 1998.
  44. E. Agustsson, R. Timofte, S. Escalera, X. Baro, I. Guyon, and R. Rothe., “Apparent and real age estimation in still images with deep residual regressors on appa-real database,,” in International Conference on Automatic Face and Gesture Recognition (FGR).   IEEE, 2017.
  45. Zhang, Zhifei, Song, Yang, Qi, and Hairong, “Age progression/regression by conditional adversarial autoencoder,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).   IEEE, 2017, pp. 4352–4360.
  46. D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” in Proceedings of the International Conference on Learning Representations (ICLR), Y. Bengio and Y. LeCun, Eds., 2015.
  47. N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-end object detection with transformers,” in Proceedings of the European Conference on Computer Vision (ECCV), A. Vedaldi, H. Bischof, T. Brox, and J.-M. Frahm, Eds.   Cham: Springer International Publishing, 2020, pp. 213–229.
  48. M. Wang, W. Deng, J. Hu, X. Tao, and Y. Huang, “Racial faces in the wild: Reducing racial bias by information maximization adaptation network,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019, pp. 692–702.
  49. K. S. Krishnapriya, V. Albiero, K. Vangara, M. C. King, and K. W. Bowyer, “Issues related to face recognition accuracy varying based on race and skin tone,” IEEE Transactions on Technology and Society, vol. 1, no. 1, pp. 8–20, 2020.
  50. A. Puc, V. Štruc, and K. Grm, “Analysis of race and gender bias in deep age estimation models,” in European Signal Processing Conference (EUSIPCO), 2021, pp. 830–834.
  51. E. D. Cubuk, B. Zoph, J. Shlens, and Q. V. Le, “Randaugment: Practical automated data augmentation with a reduced search space,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).   IEEE, 2020, pp. 3008–3017.
  52. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proceedings of the International Conference on Learning Representations (ICLR), Y. Bengio and Y. LeCun, Eds., 2015.
  53. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
  54. J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “Arcface: Additive angular margin loss for deep face recognition,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4685–4694.
  55. T. He, Z. Zhang, H. Zhang, Z. Zhang, J. Xie, and M. Li, “Bag of tricks for image classification with convolutional neural networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 558–567.
  56. L. Liu, H. Jiang, P. He, W. Chen, X. Liu, J. Gao, and J. Han, “On the variance of the adaptive learning rate and beyond,” vol. abs/1908.03265, 2020.
  57. M. R. Zhang, J. Lucas, J. Ba, and G. E. Hinton, “Lookahead optimizer: k steps forward, 1 step back,” in Advances in Neural Information Processing Systems (NIPS), H. M. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché-Buc, E. B. Fox, and R. Garnett, Eds., 2019, pp. 9593–9604.
  58. I. Loshchilov and F. Hutter, “SGDR: stochastic gradient descent with warm restarts,” in Proceedings of the International Conference on Learning Representations (ICLR).   OpenReview.net, 2017.
  59. H. Sun, H. Pan, H. Han, and S. Shan, “Deep conditional distribution learning for age estimation,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 4679–4690, 2021.
  60. S. Li and K.-T. Cheng, “Facial age estimation by deep residual decision making,” arXiv preprint arXiv:1908.10737, 2019.
  61. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems (NIPS), F. Pereira, C. Burges, L. Bottou, and K. Weinberger, Eds., vol. 25.   Curran Associates, Inc., 2012.
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now