Understand
Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures.
- Patches from the same texture are consistently classified as being more similar then patches from different textures.
- Samples synthesized from the model capture spatial correlations on scales much larger then the receptive field size, and sometimes even rival or surpass the perceptual quality of state of the art texture models (but show less variability).
- The current state of the art in parametric texture synthesis relies on the multi-layer feature space of deep CNNs that were trained on natural images.
Built on
B. Julesz, “Visual pattern discrimination,” IRE Transactions on Information Theory
1962
Earlier work this paper cites.
E. Jaynes, “On the rationale of maximum-entropy methods,” Proceedings of the IEEE
1982
Earlier work this paper cites.
D. J. Heeger and J. R. Bergen, “Pyramid-based texture analysis/synthesis,” in Proceedings of the 22Nd Annual Conference on Computer Graphics and Interactive Techniques
1995
Earlier work this paper cites.
S. C. Zhu, Y. N. Wu, and D. Mumford, “Minimax entropy principle and its application to texture modeling.,” Neural Computation
1997
Earlier work this paper cites.
J. Portilla and E. P. Simoncelli, “A parametric texture model based on joint statistics of complex wavelet coefficients,” Int. J. Comput. Vision
2000
Earlier work this paper cites.
Similar
S. C. Zhu, X. Liu, and Y. N. Wu, “Exploring texture ensembles by efficient markov chain monte carlo-toward a ’trichromacy’ theory of texture,” IEEE Trans. Pattern Anal. Mach. Intell
2000
Cited alongside, same era.
R. Rubinstein, M. Zibulevsky, and M. Elad, “Efficient implementation of the k-svd algorithm using batch orthogonal matching pursuit,” 2009
2009
Cited alongside, same era.
X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” in Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS’10)
2010
Cited alongside, same era.
J. Bruna and S. Mallat, “Audio texture synthesis with scattering moments.,” CoRR
2013
Cited alongside, same era.
2014
Cited alongside, same era.
Then
L. A. Gatys, A. S. Ecker, and M. Bethge, “Texture synthesis using convolutional neural networks,” in Advances in Neural Information Processing Systems 28
2015
Later among the works it cites.
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, “ImageNet Large Scale Visual Recognition Challenge,” International Journal of Computer Vision (IJCV)
2015
Later among the works it cites.
S. Dieleman, J. Schlüter, C. Raffel, E. Olson, S. K. Sønderby, D. Nouri, D. Maturana, M. Thoma, and other contributors, “Lasagne: First release.,” Aug. 2015
2015
Later among the works it cites.
2016
Closest in time.
[Online; accessed 2016-05-12]
E. Jones, T. Oliphant, P. Peterson, et al · 2016
Closest in time.
Beyond the bibliography
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…