Abstract
We present an LMDE method with a novel network structure and an effective joint loss function, which takes advantage of both the triplet loss function and the hinge loss function. The minimization of the joint loss function ensures that the intra-class variability of the features belonging to the same class is reduced and the inter-class separability of the features from different classes is increased. As shown in the experiments, the proposed LMDE method significantly outperforms several other state-of-the-art aesthetic classification methods in terms of classification accuracy.
This is a preview of subscription content, log in via an institution to check access.
References
Tang X O, Luo W, Wang X G. Content-based photo quality assessment. IEEE Trans Multimedia, 2013, 15: 1930–1943
Datta R, Joshi D, Li J, et al. Studying aesthetics in photographic images using a computational approach. In: Proceedings of European Conference on Computer Vision, 2006. 288–301
Guo G J, Wang H Z, Shen C H, et al. Automatic image cropping for visual aesthetic enhancement using deep neural networks and cascaded regression. IEEE Trans Multimedia, 2018, 20: 2073–2085
Pang Y W, Wang S, Yuan Y. Learning regularized LDA by clustering. IEEE Trans Neural Netw Learn Syst, 2014, 25: 2191–2201
Krizhevsky A, Sutskever I, Hinton G H. ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, 2012. 1097–1105
Jiang X H, Pang Y W, Sun M L, et al. Cascaded subpatch networks for effective CNNs. IEEE Trans Neural Netw Learn Syst, 2018, 29: 2684–2694
Schroff F, Kalenichenko D, Philbin J. Facenet: a unified embedding for face recognition and clustering. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2015. 815–823
Rojas R. Neural Networks: A Systematic Introduction. Berlin: Springer, 1996
Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res, 2011, 12: 2121–2159
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant Nos. U1605252, 61872307, 61472334, 61571379), National Key R&D Program of China (Grant No. 2017YFB1302400), and UM Multi-Year Research (Grant No. MYRG2017-00218-FST).
Author information
Authors and Affiliations
Corresponding author
Supplementary File
Rights and permissions
About this article
Cite this article
Guo, G., Wang, H., Yan, Y. et al. Large margin deep embedding for aesthetic image classification. Sci. China Inf. Sci. 63, 119101 (2020). https://doi.org/10.1007/s11432-018-9567-8
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-018-9567-8