Fast image classification algorithms based on sequential analysis

A. V. Savchenko

Zapiski Nauchnykh Seminarov POMI, Investigations on applied mathematics and informatics. Part I, Tome 499 (2021), pp. 267-283

Résumé

In this paper fast image recognition techniques based on statistical sequential analysis are discussed. We examine the possibility to sequentially process the principal components and organize a convolutional neural network with early exits. Particular attention is paid to sequentially learn multi-task lightweight neural network model to predict several facial attributes (age, gender and ethnicity) based on preliminary training on the face classification task. It is highlighted that the whole above-mentioned model should be fine-tuned in order to deal with emotion recognition problem. Experimental study on several datasets demonstrate that the proposed approach is rather accurate and has very low run-time and space complexity when compared to known state-of-the-art methods.

Bibliographie

[1] Y. Benjamini, Y. Hochberg, “Controlling the false discovery rate: a practical and powerful approach to multiple testing”, J. the Royal statistical society: series B (Methodological), 57:1 (1995), 289–300 | DOI | MR | Zbl

[2] Q. Cao, Li Shen, W. Xie, O. M. Parkhi, A. Zisserman, “VGGFace2: A dataset for recognising faces across pose and age”, Proceedings of the 13th IEEE International Conference on Automatic Face Gesture Recognition, FG, 2018, 67–74

[3] A. Das, A. Dantcheva, F. Bremond, “Mitigating bias in gender, age and ethnicity classification: A multi-task convolution neural network approach”, Proceedings of the European Conference on Computer Vision, ECCV, Springer, 2018, 573–585

[4] J. Deng, J. Guo, X. Niannan, S. Zafeiriou, “Arcface: Additive angular margin loss for deep face recognition”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2019, 4690–4699

[5] E. Eidinger, R. Enbar, T. Hassner, “Age and gender estimation of unfiltered faces”, IEEE Transactions on Information Forensics and Security, 9:12 (2014), 2170–2179 | DOI

[6] I. Goodfellow, Y. Bengio, A. Courville, Deep learning, MIT press, 2016 | Zbl

[7] S. Hung, J.-H. Lee, T. Wan, C.-H. Chen, Y.-M. Chan, C.-S. Chen, “Increasingly packing multiple facial-informatics modules in a unified deep-learning model via lifelong learning”, Proceedings of the 2019 on International Conference on Multimedia Retrieval, ICMR, 2019, 339–343 | DOI

[8] A. Mollahosseini, B. Hasani, M. H. Mahoor, “AffectNet: A database for facial expression, valence, and arousal computing in the wild”, IEEE Transactions on Affective Computing, 10:1 (2017), 18–31 | DOI

[9] P. Panda, A. Sengupta, K. Roy, “Conditional deep learning for energy-efficient and enhanced pattern recognition”, Proceedings of IEEE Design, Automation Test in Europe Conference Exhibition, 2016, 475–480

[10] O. M. Parkhi, A. Vedaldi, A. Zisserman, “Deep face recognition”, Proceedings of the British Machine Vision Conference, BMVC, v. 3, 2015

[11] R. Rothe, R. Timofte, L. Van Gool, “DEX: Deep expectation of apparent age from a single image”, Proceedings of the IEEE International Conference on Computer Vision Workshops, 2015, 10–15

[12] A. V. Savchenko, Search techniques in intelligent classification systems, Springer, 2016 | Zbl

[13] A. V. Savchenko, “Metod maksimalno pravdopodobnykh rassoglasovanii v zadache raspoznavaniya izobrazhenii na osnove glubokikh neironnykh setei”, Kompyuternaya optika, 41:3 (2017), 422–430

[14] A. V. Savchenko, “Efficient facial representations for age, gender and identity recognition in organizing photo albums using multi-output ConvNet”, PeerJ Computer Science, 5 (2019), e197 | DOI

[15] A. V. Savchenko, “Sequential three-way decisions in multi-category image recognition with deep features based on distance factor”, Information Sciences, 489 (2019), 18–36 | DOI | MR | Zbl

[16] A. V. Savchenko, “Probabilistic neural network with complex exponential activation functions in image recognition”, IEEE Transactions on Neural Networks and Learning Systems, 31:2 (2020), 651–660 | DOI | MR

[17] A. V. Savchenko, “Sequential analysis with specified confidence level and adaptive convolutional neural networks in image recognition”, Proceedings of the IEEE International Joint Conference on Neural Networks, IJCNN, 2020

[18] F. Schroff, D. Kalenichenko, J. Philbin, “FaceNet: A unified embedding for face recognition and clustering”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2015, 815–823

[19] S. C. Schwartz, “Estimation of probability density by an orthogonal series”, The Annals of Mathematical Statistics, 1967, 1261–1265 | DOI | Zbl

[20] D. F. Specht, “Probabilistic neural networks”, Neural Networks, 3:1 (1990), 109–118 | DOI

[21] S. Teerapittayanon, B. McDanel, H.T. Kung, “BranchyNet: Fast inference via early exiting from deep neural networks”, Proceedings of the 23rd IEEE International Conference on Pattern Recognition, ICPR, 2016, 2464–2469

[22] A. Wald, Sequential Analysis, Dover Publications, New York, 2013

[23] Y. Y. Yao, X. F. Deng, “Sequential three-way decisions with probabilistic rough sets”, Proceedings of ICCI*CC, IEEE Computer Society, 2011, 120–125

[24] Z. Zhang, Y. Song, H. Qi, “Age progression/regression by conditional adversarial autoencoder”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017, 5810–5818