Feature Discovery by Deep Learning for Aesthetic Analysis of Evolved Abstract Images

Aus de_evolutionary_art_org
Version vom 15. November 2015, 14:39 Uhr von Gubachelier (Diskussion | Beiträge) (Used References)

(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu: Navigation, Suche

Referenz

Allan Campbell, Vic Ciesielksi, A. K. Qin: Feature Discovery by Deep Learning for Aesthetic Analysis of Evolved Abstract Images. In: EvoMUSART 2015, 27-38.

DOI

http://link.springer.com/chapter/10.1007/978-3-319-16498-4_3

Abstract

We investigated the ability of a Deep Belief Network with logistic nodes, trained unsupervised by Contrastive Divergence, to discover features of evolved abstract art images. Two Restricted Boltzmann Machine models were trained independently on low and high aesthetic class images. The receptive fields (filters) of both models were compared by visual inspection. Roughly 10 % of these filters in the high aesthetic model approximated the form of the high aesthetic training images. The remaining 90 % of filters in the high aesthetic model and all filters in the low aesthetic model appeared noise like. The form of discovered filters was not consistent with the Gabor filter like forms discovered for MNIST training data, possibly revealing an interesting property of the evolved abstract training images. We joined the datasets and trained a Restricted Boltzmann Machine finding that roughly 30 % of the filters approximate the form of the high aesthetic input images. We trained a 10 layer Deep Belief Network on the joint dataset and used the output activities at each layer as training data for traditional classifiers (decision tree and random forest). The highest classification accuracy from learned features (84 %) was achieved at the second hidden layer, indicating that the features discovered by our Deep Learning approach have discriminative power. Above the second hidden layer, classification accuracy decreases.

Extended Abstract

Bibtex

@incollection{
year={2015},
isbn={978-3-319-16497-7},
booktitle={Evolutionary and Biologically Inspired Music, Sound, Art and Design},
volume={9027},
series={Lecture Notes in Computer Science},
editor={Johnson, Colin and Carballal, Adrian and Correia, João},
doi={10.1007/978-3-319-16498-4_3},
title={Feature Discovery by Deep Learning for Aesthetic Analysis of Evolved Abstract Images},
url={http://dx.doi.org/10.1007/978-3-319-16498-4_3 http://de.evo-art.org/index.php?title=Feature_Discovery_by_Deep_Learning_for_Aesthetic_Analysis_of_Evolved_Abstract_Images },
publisher={Springer International Publishing},
keywords={Computational aesthetics; Deep learning; Evolved abstract images},
author={Campbell, Allan and Ciesielksi, Vic and Qin, A.K.},
pages={27-38},
language={English}
}

Used References

1. Birkhoff, GD (1933) Aesthetic Measure. Mass, Cambridge http://dx.doi.org/10.4159/harvard.9780674734470

2. Campbell, A., Ciesielski, V., Trist, K.: A self organizing map based method for understanding features associated with high aesthetic value evolved abstract images. In: 2014 IEEE Congress on Evolutionary Computation (CEC), pp. 2274–2281. IEEE (2014)

3. Ciesielski, V, Barile, P, Trist, K Finding image features associated with high Aesthetic value by machine learning. In: Machado, P, McDermott, J, Carballal, A eds. (2013) Evolutionary and Biologically Inspired Music, Sound, Art and Design. Springer, Heidelberg, pp. 47-58 http://dx.doi.org/10.1007/978-3-642-36955-1_5

4. Datta, R.: Semantics and aesthetics inference for image search: statistical learning approaches. Pennsylvania State University (2009)

5. Datta, R, Joshi, D, Li, J, Wang, JZ Studying Aesthetics in photographic images using a computational approach. In: Leonardis, A, Bischof, H, Pinz, A eds. (2006) Computer Vision – ECCV 2006. Springer, Heidelberg, pp. 288-301 http://dx.doi.org/10.1007/11744078_23

6. Erhan, D., Bengio, Y., Courville, A., Vincent, P.: Visualizing higher-layer features of a deep network. Dept. IRO, Université de Montréal, Technical report (2009)

7. Fischer, A, Igel, C (2014) Training restricted boltzmann machines: An introduction. Pattern Recogn. 47: pp. 25-39 http://dx.doi.org/10.1016/j.patcog.2013.05.025

8. Galanter, P Computational aesthetic evaluation: past and future. In: McCormack, J, d’Inverno, M eds. (2012) Computers and Creativity. Springer, Heidelberg, pp. 255-293 http://dx.doi.org/10.1007/978-3-642-31727-9_10

9. Ginosar, S., Haas, D., Brown, T., Malik, J.: Detecting people in cubist art. arXiv preprint arXiv:1409.6235 (2014) http://arxiv.org/abs/1409.6235

10. Hall, M, Frank, E, Holmes, G, Pfahringer, B, Reutemann, P, Witten, IH (2009) The weka data mining software: an update. ACM SIGKDD Explor. Newslett. 11: pp. 10-18 http://dx.doi.org/10.1145/1656274.1656278

11. Hinton, G (2010) A practical guide to training restricted Boltzmann machines. Momentum 9: pp. 926

12. Hinton, G, Osindero, S, Teh, Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput. 18: pp. 1527-1554 http://dx.doi.org/10.1162/neco.2006.18.7.1527

13. Geoffrey, E (2002) Training products of experts by minimizing contrastive divergence. Neural Comput. 14: pp. 1771-1800 http://dx.doi.org/10.1162/089976602760128018

14. Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 (2012) http://arxiv.org/abs/1207.0580

15. Hoenig, F Defining computational aesthetics. In: Neumann, L, Sbert, M, Gooch, B, Purgathofer, W eds. (2005) Computational Aesthetics. Eurographics Association, London, pp. 13-18

16. Ke, Y., Tang, X., Jing, F.: The design of high-level features for photo quality assessment. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 419–426. IEEE (2006)

17. LeCun, Y., Cortes, C.: The mnist database of handwritten digits (1998)

18. Lee, H, Ekanadham, C, Ng, AY Sparse deep belief net model for visual area v2. In: Platt, JC, Koller, D, Singer, Y, Roweis, S eds. (2008) Advances in Neural Information Processing Systems. MIT Press, Cambridge, pp. 873-880

19. Lu, X., Lin, Z., Jin, H., Yang, J., Wang, J.Z.: Rapid: Rating pictorial aesthetics using deep learning. In: Proceedings of the ACM International Conference on Multimedia, pp. 457–466. ACM (2014)

20. Machado, P., Cardoso, A.: Generation and evaluation of artworks. In: Proceedings of the 1st European Workshop on Cognitive Modeling, CM’96, pp. 96–39 (2010)

21. Murray, N., Marchesotti, L., Perronnin, F.: Ava: A large-scale database for aesthetic visual analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2408–2415. IEEE (2012)

22. Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 807–814 (2010)

23. Reaves, D.: Aesthetic image rating (AIR) algorithm. Ph.D. thesis (2008) http://www.cs.utexas.edu/ftp/techreports/honor_theses/cs-08-04-reaves.pdf

24. Simard, P.Y., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: 2013 12th International Conference on Document Analysis and Recognition, vol. 2, pp. 958–958. IEEE Computer Society (2003)

25. Spratt, E.L., Elgammal, A.: Computational beauty: Aesthetic judgment at the intersection of art and science. arXiv preprint arXiv:1410.2488 (2014) http://arxiv.org/abs/1410.2488

26. Jost Tobias Springenberg and Martin Riedmiller. Improving deep neural networks with probabilistic maxout units. arXiv preprint arXiv:1312.6116 (2013) http://arxiv.org/abs/1312.6116

27. Xu, Q., D’Souza, D., Ciesielski, V.: Evolving images for entertainment. In: Proceedings of the 4th Australasian Conference on Interactive Entertainment, p. 26. RMIT University (2007)

Links

Full Text

internal file


Sonstige Links

http://www.researchgate.net/researcher/8135404_Victor_Ciesielski