Abstract
Label distribution learning achieved promising results on ordinal regression tasks such as facial age and attractiveness estimation, especially using deep label distribution learning (DLDL) methods, introducing the label distribution learning into deep convolutional neural networks. However, existing DLDL methods have an inconsistency between the training objectives and the evaluation metric, so they may be suboptimal. In addition, these methods always adopt image classification or face recognition models with a large amount of parameters, which carry expensive computation cost and storage overhead. In this paper, we firstly analyze the essential relationship between two state-of-the-art methods (ranking CNN and DLDL) and show that the ranking method is in fact learning label distribution implicitly. This result thus firstly unifies two existing popular state-of-the-art methods into the DLDL framework. Second, in order to alleviate the inconsistency and reduce resource consumption, we design a lightweight network architecture and propose a unified framework which can jointly learn label distribution and regress expectation value. The effectiveness of our approach has been demonstrated on typical ordinal regression tasks including facial age and attractiveness estimation. Our method achieves new state-of-the-art results using the single model with 36× fewer parameters and 3× faster inference speed.
Similar content being viewed by others
Notes
0.5 compression rate means every Conv layer has only 50% channels as that in VGG-16.
References
Escalera S, Fabian J, Pardo P, Baró" X, Gonzalez J, Escalante HJ, Misevic D, Steiner U, Guyon I (2015) ChaLearn looking at people 2015: apparent age and cultural event recognition datasets and results. In: Proceeding of the IEEE international conference on computer vision workshop
Deng Y, Loy CC, Tang X (2017) Image aesthetic assessment: an experimental survey. IEEE Signal Proces Mag 34(4):80–106
Lebedeva I, Guo Y, Ying F (2022) Mebeauty: a multi-ethnic facial beauty dataset in-the-wild. Neural Comput Appl 34(17):14169–14183
Schwarz A, Haurilet M, Martinez M, Stiefelhagen R (2017) DriveAHead: a Large-scale driver head pose dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops
Li X, Zhao H, Wang Z, Yu Z (2020) Research on movie rating prediction algorithms. In: 2020 5th IEEE international conference on big data analytics (ICBDA)
Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Parkhi OM, Vedaldi A, Zisserman A et al (2015) Deep face recognition. In: Proceedings of the British machine vision conference
Guo Y, Zhang L, Hu Y, He X, Gao J (2016) MS-Celeb-1M: a dataset and benchmark for large-scale face recognition. In: Proceedings of the European conference on computer vision
Shakeel MS, Lam K-M (2019) Deep-feature encoding-based discriminative model for age-invariant face recognition. Pattern Recognit 93:442–457
Ranjan R, Sankaranarayanan S, Castillo CD, Chellappa R (2017) An all-in-one convolutional neural network for face analysis. In: Proceedings of the IEEE conference on automatic face and gesture recognition
Rothe R, Timofte R, Van Gool L (2016) Deep expectation of real and apparent age from a single image without facial landmarks. Int J Comput Vis 126(2):144–157
Gao B-B, Xing C, Xie C-W, Wu J, Geng X (2017) Deep label distribution learning with label ambiguity. IEEE Trans Image Process 26(6):2825–2838
Niu Z, Zhou M, Wang L, Gao X, Hua G (2016) Ordinal regression with multiple output CNN for age estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Chen S, Zhang C, Dong M, Le J, Rao M (2017) Using ranking-CNN for age estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Chen S, Zhang C, Dong M (2017) Deep age estimation: from classification to ranking. IEEE Trans Multimed 20(8):2209–2222
Fan Y-Y, Liu S, Li B, Guo Z, Samal A, Wan J, Li SZ (2017) Label distribution-based facial attractiveness computation by deep residual learning. IEEE Trans Multimed 20(8):2196–2208
Rodríguez P, Cucurull G, Gonfaus JM, Roca FX, Gonzalez J (2017) Age and gender recognition in the wild with deep attention. Pattern Recognit 72:563–571
Antipov G, Baccouche M, Berrani S-A, Dugelay J-L (2016) Apparent age estimation from face images combining general and children-specialized deep learning models. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshop
Tan Z, Yang Y, Wan J, Guo G, Li SZ (2019) Deeply-learned hybrid representations for facial age estimation. In: Proceedings of the international joint conference on artificial intelligence, p 3548–3554
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of the international conference on learning representations
Luo J-H, Wu J, Lin W (2017) ThiNet: a filter level pruning method for deep neural network compression. In: Proceedings of the IEEE international conference on computer vision
Greco A, Saggese A, Vento M, Vigilante V (2021) Effective training of convolutional neural networks for age estimation based on knowledge distillation. Neural Computing and Applications, 1–16
Escalera S, Torres Torres M, Martinez B, Baró" X, Jair Escalante H, Guyon I, Tzimiropoulos G, Corneou C, Oliu M, Ali Bagheri M et al (2016) ChaLearn looking at people and faces of the world: face analysis workshop and challenge 2016. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshop
Zhang Z, Song Y, Qi H (2017) Age progression/regression by conditional adversarial autoencoder. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Ricanek K, Tesafaye T (2006) Morph: A longitudinal image database of normal adult age-progression. In: Proceedings of the IEEE conference on automatic face and gesture recognition
Xie D, Liang L, Jin L, Xu J, Li M (2015) SCUT-FBP: a benchmark dataset for facial beauty perception. In: IEEE international conference on systems, man, and cybernetics
Ma DS, Correll J, Wittenbrink B (2015) The Chicago face database: a free stimulus set of faces and norming data. Behav Res Methods 47(4):1122–1135
Geng X (2016) Label distribution learning. IEEE Trans Knowl Data Eng 28(7):1734–1748
Gao B-B, Zhou H-Y, Wu J, Geng X (2018) Age estimation using expectation of label distribution learning. In: Proceedings of the international joint conference on artificial intelligence
Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6):681–685
Guo G, Mu G, Fu Y, Huang TS (2009) Human age estimation using bio-inspired features. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Zhang D, Zhao Q, Chen F (2011) Quantitative analysis of human facial beauty using geometric features. Pattern Recognit 44(4):940–950
Kagian A, Dror G, Leyvand T, Cohen-Or D, Ruppin E (2007) A humanlike predictor of facial attractiveness. Proc. Advances in Neural Information Processing Systems
Huang D, Han L, De la Torre F (2017) Soft-margin mixture of regressions. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Chang K-Y, Chen C-S, Hung Y-P (2011) Ordinal hyperplanes ranker with cost sensitivities for age estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Chen K, Gong S, Xiang T, Change Loy C (2013) Cumulative attribute space for age and crowd density estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Li C, Liu Q, Dong W, Zhu X, Liu J, Lu H (2015) Human age estimation based on locality and ordinal information. IEEE Trans Cybern 45(11):2522–2534
Geng X, Yin C, Zhou Z-H (2013) Facial age estimation by learning from label distributions. IEEE Trans Pattern Anal Mach Intell 35(10):2401–2412
Ren Y, Geng X (2017) Sense beauty by label distribution learning. In: Proceedings of the international joint conference on artificial intelligence
Xing C, Geng X, Xue H (2016) Logistic boosting regression for label distribution learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition
He Z, Li X, Zhang Z, Wu F, Geng X, Zhang Y, Yang M-H, Zhuang Y (2017) Data-dependent label distribution learning for age estimation. IEEE Trans Image Process 26(8):3846–3858
Shen W, Zhao K, Guo Y, Yuille A (2017) Label distribution learning forests. In: Proceedings of the 31st conference on neural information processing systems
Hu Z, Wen Y, Wang J, Wang M, Hong R, Yan S (2017) Facial age estimation with age difference. IEEE Trans Image Process 26(7):3087–3097
Yang J, She D, Sun M (2017) Joint image emotion classification and distribution learning via deep convolutional neural network. In: Proceedings of the international joint conference on artificial intelligence
Shen W, Guo Y, Wang Y, Zhao K, Wang B, Yuille AL (2018) Deep regression forests for age estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the international conference on machine learning
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499–1503
Berg A, Oskarsson M, O’Connor M (2021) Deep ordinal regression with label diversity. In: Proceedings of the 25th international conference on pattern recognition
Savchenko AV (2019) Efficient facial representations for age, gender and identity recognition in organizing photo albums using multi-output convnet. PeerJ Comput Sci 5:e197
Han H, Otto C, Liu X, Jain AK (2015) Demographic estimation from face images: human versus machine performance. IEEE Trans Pattern Anal Mach Intell 37(6):1148–1161
Antipov G, Baccouche M, Berrani S-A, Dugelay J-L (2017) Effective training of convolutional neural networks for face-based gender and age prediction. Pattern Recognit 72:15–26
Pan H, Han H, Shan S, Chen X (2018) Mean-variance loss for deep age estimation from a face. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Tan Z, Wan J, Lei Z, Zhi R, Guo G, Li SZ (2018) Efficient group-n encoding and decoding for facial age estimation. IEEE Trans Pattern Anal Mach Intell 40(11):2610–2623
Zhang C, Liu S, Xu X, Zhu C (2019) C3AE: Exploring the limits of compact model for age estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Li W, Lu J, Feng J, Xu C, Zhou J, Tian Q (2019) Bridgenet: A continuity-aware probabilistic network for age estimation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Liu H, Sun P, Zhang J, Wu S, Yu Z, Sun X (2020) Similarity-aware and variational deep adversarial learning for robust facial age estimation. IEEE Trans Multimed 22(7):1808–1822
Lim K, Shin N-H, Lee Y-Y, Kim C-S (2020) Order learning and its application to age estimation. In: Proceedings of the international conference on learning representations
Li W, Huang X, Lu J, Feng J, Zhou J (2021) Learning probabilistic ordinal embeddings for uncertainty-aware regression. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Deng Z, Liu H, Wang Y, Wang C, Yu Z, Sun X (2021) PML: progressive margin loss for long-tailed age classification. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Liu H, Lu J, Feng J, Zhou J (2017) Ordinal deep learning for facial age estimation. IEEE Trans Circuits Syst Video Technol 29(2):486–501
Huo Z, Yang X, Xing C, Zhou Y, Hou P, Lv J, Geng X (2016) Deep age distribution learning for apparent age estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops
Uricár M, Timofte R, Rothe R, Matas J, Van Gool L (2016) Structured output svm prediction of apparent age, gender and smile from deep features. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops
Cao W, Mirjalili V, Raschka S (2020) Rank consistent ordinal regression for neural networks with application to age estimation. Pattern Recognit Lett 140:325–331
Gustafsson FK, Danelljan M, Bhat G, Schön TB (2020) Energy-based models for deep probabilistic regression. In: Proceedings of the European conference on computer vision
Lin L, Liang L, Jin L (2018) R2-ResNeXt: A ResNeXt-based regression model with relative ranking for facial beauty prediction. In: Proceedings of the 24th international conference on pattern recognition
Chen L, Deng W (2019) Facial attractiveness prediction by deep adaptive label distribution learning. In: Proceedings of the Chinese conference on biometric recognition
Xu J (2021) Mt-resnet: a multi-task deep network for facial attractiveness prediction. In: Proceedings of the 2nd international conference on computing and data science
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Proceedings of the European conference on computer vision
Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP (2018) Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology f278(1):313–322
Kalayeh MM, Seifu M, LaLanne W, Shah M (2015) How to Take a Good Selfie?. In: Proceedings of the the 23rd annual ACM conference on multimedia conference
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
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 (e.g. a society or other partner) 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.
About this article
Cite this article
Gao, BB. Jointly learning distribution and expectation in a unified framework for facial age and attractiveness estimation. Neural Comput & Applic 35, 15583–15599 (2023). https://doi.org/10.1007/s00521-023-08563-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08563-4