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

Multi-Task Learning Using Uncertainty to Weigh Losses for Heterogeneous Face Attribute Estimation (2403.00561v1)

Published 1 Mar 2024 in cs.CV and cs.AI

Abstract: Face images contain a wide variety of attribute information. In this paper, we propose a generalized framework for joint estimation of ordinal and nominal attributes based on information sharing. We tackle the correlation problem between heterogeneous attributes using hard parameter sharing of shallow features, and trade-off multiple loss functions by considering homoskedastic uncertainty for each attribute estimation task. This leads to optimal estimation of multiple attributes of the face and reduces the training cost of multitask learning. Experimental results on benchmarks with multiple face attributes show that the proposed approach has superior performance compared to state of the art. Finally, we discuss the bias issues arising from the proposed approach in face attribute estimation and validate its feasibility on edge systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (30)
  1. H. Proença, “The uu-net: Reversible face de-identification for visual surveillance video footage,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 2, pp. 496–509, 2021.
  2. X. Yin, Y. Tai, Y. Huang, and X. Liu, “Fan: Feature adaptation network for surveillance face recognition and normalization,” in Proceedings of the Asian Conference on Computer Vision, 2020.
  3. 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.
  4. Z. Zhao, P. Qian, Y. Hou, and Z. Zeng, “Adaptive mean-residue loss for robust facial age estimation,” in 2022 IEEE International Conference on Multimedia and Expo (ICME), 2022, pp. 1–6.
  5. Y. Sun, M. Zhang, Z. Sun, and T. Tan, “Demographic analysis from biometric data: Achievements, challenges, and new frontiers,” IEEE transactions on pattern analysis and machine intelligence, vol. 40, no. 2, pp. 332–351, 2017.
  6. F. Wang, H. Han, S. Shan, and X. Chen, “Deep multi-task learning for joint prediction of heterogeneous face attributes,” in 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), 2017, pp. 173–179.
  7. M. D. Zeiler and R. Fergus, “Visualizing and understanding convolutional networks,” in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13.   Springer, 2014, pp. 818–833.
  8. H. Han, A. K. Jain, F. Wang, S. Shan, and X. Chen, “Heterogeneous face attribute estimation: A deep multi-task learning approach,” IEEE transactions on pattern analysis and machine intelligence, vol. 40, no. 11, pp. 2597–2609, 2017.
  9. S. Ruder, “An overview of multi-task learning in deep neural networks,” arXiv preprint arXiv:1706.05098, 2017.
  10. J. Baxter, “A bayesian/information theoretic model of learning to learn via multiple task sampling,” Machine learning, vol. 28, pp. 7–39, 1997.
  11. M. Tan and Q. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” in International conference on machine learning.   PMLR, 2019, pp. 6105–6114.
  12. A. Kendall, Y. Gal, and R. Cipolla, “Multi-task learning using uncertainty to weigh losses for scene geometry and semantics,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7482–7491.
  13. 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.
  14. Z. Zhang, Y. Song, and H. Qi, “Age progression/regression by conditional adversarial autoencoder,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 5810–5818.
  15. A. Garain, B. Ray, P. K. Singh, A. Ahmadian, N. Senu, and R. Sarkar, “Gra__\__net: A deep learning model for classification of age and gender from facial images,” IEEE Access, vol. 9, pp. 85 672–85 689, 2021.
  16. Z. Shen, C. Cui, J. Huang, J. Zong, M. Chen, and Y. Yin, “Deep adaptive feature aggregation in multi-task convolutional neural networks,” in Proceedings of the 29th ACM International Conference on Information & Knowledge Management, ser. CIKM ’20.   New York, NY, USA: Association for Computing Machinery, 2020, p. 2213–2216. [Online]. Available: https://doi.org/10.1145/3340531.3412132
  17. K. Zhang, C. Gao, L. Guo, M. Sun, X. Yuan, T. X. Han, Z. Zhao, and B. Li, “Age group and gender estimation in the wild with deep ror architecture,” IEEE Access, vol. 5, pp. 22 492–22 503, 2017.
  18. E. P. Ijjina, G. Kanahasabai, and A. S. Joshi, “Deep learning based approach to detect customer age, gender and expression in surveillance video,” in 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2020, pp. 1–6.
  19. I. Rafique, A. Hamid, S. Naseer, M. Asad, M. Awais, and T. Yasir, “Age and gender prediction using deep convolutional neural networks,” in 2019 International Conference on Innovative Computing (ICIC), 2019, pp. 1–6.
  20. A. Saha, S. N. Kumar, and P. Nithyakani, “Age and gender prediction using adaptive gamma correction and convolutional neural network,” in 2023 International Conference on Computer Communication and Informatics (ICCCI).   IEEE, 2023, pp. 1–5.
  21. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  22. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
  23. G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700–4708.
  24. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
  25. U. Jamoliddin and J. H. Yoo, “Age and gender classification with small scale cnn,” The Journal of the Korea institute of electronic communication sciences, vol. 17, no. 1, pp. 99–104, 2022.
  26. W. Li, X. Huang, J. Lu, J. Feng, and J. Zhou, “Learning probabilistic ordinal embeddings for uncertainty-aware regression,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 13 896–13 905.
  27. M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510–4520.
  28. S. Kothari, S. Deshmukh, and S. Mehta, “Comparison of age, gender and ethnicity prediction using traditional cnn and transfer learning,” in 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2022, pp. 1–4.
  29. F. Schroff, D. Kalenichenko, and J. Philbin, “Facenet: A unified embedding for face recognition and clustering,” in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 815–823.
  30. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 618–626.

Summary

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

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