Skip to main content
SpringerLink
Log in

AW-GAN: face aging and rejuvenation using attention with wavelet GAN

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Most existing state-of-the-art face aging models primarily focus on an adult or long-span aging and modeling age transformation in the image domain. This work proposes a child and adult face aging framework that captures more texture and shape information using attention with a wavelet-transformation-based generative adversarial network in the frequency domain. To facilitate child and adult age synthesis, we adopt a wavelet-based multi-scale patch discriminator, which increases the stability of model training and captures local texture details of the child and adult faces. Moreover, we introduce a modified convolutional block attention module, emphasizing only facial regions related to a target attribute and preserving the attribute-excluding details. Our new objective function, modified attention generator, and wavelet multi-scale patch discrimination has shown qualitative and quantitative improvements over the state-of-the-art approaches in terms of face recognition and age estimation on benchmarked children and adult datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. United Nations Convention on the Rights of the Child defines child as “A human being below the age of 18 years unless, under the law applicable to the child, the majority has been attained earlier” [1]

  2. We use face aging, age progression alternately in this paper.

  3. We use face de-aging, rejuvenation and age regression alternately in this paper.

  4. https://github.com/ZZUTK/Face-Aging-CAAE.

  5. https://github.com/dawei6875797/Face-Aging-with-Identity-Preserved-Conditional-Generative-Adversarial.

  6. https://github.com/davidsandberg/facenet

  7. https://github.com/seasonSH/Probabilistic-Face-Embeddings.https://github.com/seasonSH/Probabilistic-Face-Embeddings.

  8. https://github.com/deepinsight/insightface.

  9. This particular COTS is also one of the best performers in the NIST ongoing Face Recognition Vendor Test (FRVT).

References

  1. UNICEF: United nations children’s fund. www.unicef-irc.org/portfolios/crc-optional-2.html/ (2000)

  2. United nations office on drugs and crime. www.unodc.org/unodc/data-and-analysis

  3. National crime information center. www.fbi.gov/services/cjis/ncic

  4. Missing children statistics. globalmissingkids.org/awareness/missing-children-statistics/

  5. Face recognition system. https://timesofindia.indiatimes.com/city/delhi/delhi-facial-recognition-system

  6. BBC: ;little boy lost finds his mother using google earth (2014). www.bbc.com/news/magazine/

  7. Zhang Z, Song Y, Qi H (2017) Age progression/regression by conditional adversarial autoencoder. In: IEEE CVPR, pp 4352–4360

  8. Yang H, Huang D, Wang Y, Jain AK (2018) Learning face age progression: a pyramid architecture of gans. In: CVPR, pp 31–39

  9. Wang Z, Tang X, Luo W, Gao S (2018) Face aging with identity-preserved conditional generative adversarial networks. In: (CVPR), pp 7939–7947

  10. Sun Y, Tang J, Shu X, Sun Z, Tistarelli M (2020) Facial age synthesis with label distribution-guided generative adversarial network. IEEE transactions on information forensics and security pp 2679–2691

  11. Chandaliya PK, Sinha A, Nain N (2020) Childface: gender aware child face aging. In: BIOSIG, pp 255–263

  12. Deb D, Nain N, Jain AK (2018) Longitudinal study of child face recognition. In: ICB, pp 225–232

  13. Srinivas N, Ricanek K, Michalski D, Bolme DS, King, M (2019) Face recognition algorithm bias: performance differences on images of children and adults. In CVPRW, 2019, pp 2269–2277

  14. Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering In CVPR, pp 815–823

  15. Shi Y, Jain A (2019) Probabilistic face embeddings. In: (ICCV), pp 6901–6910

  16. Deng J, Guo J, Niannan X, Zafeiriou S (2019) Arcface: Additive angular margin loss for deep face recognition. In: CVPR, pp 4685–4694

  17. Patrick J Grother Mei L Ngan, K.K.H (2018) Ongoing face recognition vendor test(frvt) part 2: Identification. In: NIST interagency report

  18. Chandaliya PK, Nain N (2021) Child face age progression and regression using self-attention multi-scale patch gan. In: 2021 IEEE International joint conference on biometrics (IJCB), pp 1–8

  19. Mao X, Li Q, Xie H, Lau RYK, Wang Z, Smolley SP (2017) Least squares generative adversarial networks. In: (ICCV), pp 2813–2821

  20. Kemelmacher-Shlizerman I, Suwajanakorn S, Seitz SM (2014) Illumination-aware age progression. In: (CVPR), pp 3334–3341

  21. Wang H, Wang Y, Li Wea (2020) Adaptive morphological and bilateral filtering with ensemble convolutional neural network for pose-invariant face recognition. In: J Ambient Intell Human Comput, vol. 11, pp 1153-1162

  22. Liang Y, Xu Y, Liu L, Liao S, Zou B (2011) chap. A multi-layer model for face aging simulation, Trans. Edutainment 6 (2011), pp 182–192

  23. Ramanathan N, Chellappa R (2006) Modeling age progression in young faces. In: CVPR, pp 387–394

  24. Antipov G, Baccouche M, Dugelay J (2017) Face aging with conditional generative adversarial networks. In: ICIP, pp 2089–2093. IEEE

  25. Antipov G, Baccouche M, Dugelay J (2017) Boosting cross-age face verification via generative age normalization. In: IEEE. BTAS, pp 191–199

  26. Palsson S, Agustsson E, Timofte R, Van Gool L (2018) Generative adversarial style transfer networks for face aging. In: 2018 IEEE (CVPRW), pp 2165–21658

  27. Zhang K, Su Y, Guo X, Qi L, Zhao Z (2021) Mu-gan: Facial attribute editing based on multi-attention mechanism. IEEE/CAA J Automatica Sin 614-1626. https://doi.org/10.1109/JAS.2020.1003390

  28. Woo S, Park J, Lee JY, Kweon IS (2018) Cbam: Convolutional block attention module. In: computer vision – ECCV 2018, pp. 13–19. Springer International Publishing

  29. Yang J, Ren P, Zhang D, Chen D, Wen F, Li H, Hua G (2017) Neural aggregation network for video face recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 5216–5225 . https://doi.org/10.1109/CVPR.2017.554

  30. Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 3146–3154

  31. Cao Y, Xu J, Lin S, Wei F, Hu H (2019) Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), pp 1971–1980 . https://doi.org/10.1109/ICCVW.2019.00246

  32. Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 7132–7141

  33. Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2020) Eca-net: Efficient channel attention for deep convolutional neural networks. In: The IEEE conference on computer vision and pattern recognition (CVPR), pp 11531–11539

  34. Zhang H, Goodfellow I, Metaxas D, Odena A (2019) Self-attention generative adversarial networks. In: ICML, pp 7354–7363. PMLR

  35. Park J, Woo S, Lee JY, Kweon IS (2018) Bam: bottleneck attention module. In: BMVC, pp 1–7

  36. Wang TC, Liu MY, Zhu JY, Tao A, Kautz J, et al (2018) High-resolution image synthesis and semantic manipulation with conditional gans. In: IEEE(CVPR), pp 8798–8807

  37. Perarnau G, van de Weijer J, Raducanu B, Álvarez JM (2016) Invertible Conditional GANs for image editing. In: NIPS, pp 1–8

  38. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: NIPS, pp 1097–1105

  39. Johnson J, Alahi A, Fei-Fei L (2016) Perceptual losses for real-time style transfer and super-resolution. In: computer vision – ECCV 2016, pp 694–711

  40. Wang Z, Simoncelli E, Bovik A (2003) Multiscale structural similarity for image quality assessment. In: The thrity-seventh asilomar conference on signals, systems computers 2, pp 1398–1402

  41. Chandaliya PK, Nain N (2022) Childgan: face aging and rejuvenation to find missing children. Pattern Recogn 129:108761. https://doi.org/10.1016/j.patcog.2022.108761

    Article  Google Scholar 

  42. Chen BC, Chen CS, Hsu WH (2014) Cross-age reference coding for age-invariant face recognition and retrieval. In: ECCV

  43. Fu Y, Hospedales TM, Xiang T, Yao Y, Gong S (2014) Interestingness prediction by robust learning to rank. In: ECCV

  44. Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE signal process. Lett. pp 1499–1503

  45. Chandaliya PK, Nain N (2019) Conditional perceptual adversarial variational autoencoder for age progression and regression on child face. In: (ICB), pp 1–8

  46. Chandaliya PK, Nain N (2021) Child face age progression and regression using self-attention multi-scale patch gan. In: 2021 IEEE International joint conference on biometrics (IJCB), pp 1–8

  47. Yang TY, Huang YH, Lin YY, Hsiu PC, Chuang YY (2018) Ssr-net: a compact soft stagewise regression network for age estimation. In: IJCAI-18, pp 1078–1084

  48. Cao Q, Shen L, Xie W, Parkhi OM, Zisserman A (2018) Vggface2: A dataset for recognising faces across pose and age. In: International conference on automatic face and gesture recognition, pp 1-8

  49. Guo Y, Zhang L, Hu Y, He X, Gao J (2016) Ms-celeb-1m: a dataset and benchmark for large-scale face recognition. In: ECCV, pp 1–17

Download references

Acknowledgements

This research is based upon work supported by the Ministry of Electronics and Information Technology (Meity), Government of India, under Grant (No.4 (13)/2019-ITEA). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the TITAN V GPU used for this research.

Author information

Authors and Affiliations

  1. Malaviya National Institute of Technology Jaipur, Jaipur, India

    Praveen Kumar Chandaliya & Neeta Nain

Authors
  1. Praveen Kumar Chandaliya
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Neeta Nain
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Praveen Kumar Chandaliya.

Ethics declarations

Disclosure of potential conflicts of interest

We declare that we have no financial and personal relationships with other people or organization that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled. “AW-GAN: Face Aging and Rejuvenation using Attention with Wavelet GAN”.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chandaliya, P.K., Nain, N. AW-GAN: face aging and rejuvenation using attention with wavelet GAN. Neural Comput & Applic 35, 2811–2825 (2023). https://doi.org/10.1007/s00521-022-07721-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07721-4

Keywords

Search

Navigation