Transformation properties of learned visual representations

3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings

Volumn , Issue , 2015, Pages

  Cohen, Taco S ^a   Welling, Max ^a  

^a UNIVERSITY OF AMSTERDAM   (Netherlands)

Author keywords

[No Author keywords available]

Indexed keywords

GROUP THEORY;

GROUP REPRESENTATION; IRREDUCIBLE REPRESENTATIONS; NON-COMMUTATIVE; PARTIAL OBSERVABILITY; PERSPECTIVE PROJECTIONS; STATISTICAL DEPENDENCIES; THREE-DIMENSIONAL OBJECT; VISUAL REPRESENTATIONS;

MATHEMATICAL TRANSFORMATIONS;

EID: 85083950051     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (25)

1. Anselmi, Fabio, Leibo, Joel Z, Rosasco, Lorenzo, Mutch, Jim, Tacchetti, Andrea, and Poggio, Tomaso. Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning? Technical Report 001, MIT Center for Brains, Minds and Machines, 2014.
2. Bengio, Y., Courville, A., and Vincent, P. Representation Learning: A Review and New Perspectives. IEEE transactions on pattern analysis and machine intelligence, pp. 1–30, February 2013.
3. Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., and Bengio, Y. Theano: A CPU and GPU math compiler in Python. In Proceedings of the Python for Scientific Computing Conference (SciPy), pp. 1–7, 2010.
4. Bruna, Joan and Mallat, Stéphane. Invariant scattering convolution networks. IEEE transactions on pattern analysis and machine intelligence, 35(8):1872–86, August 2013. ISSN 1939-3539. doi: 10.1109/TPAMI.2012.230.
5. Bruna, Joan, Szlam, Arthur, and LeCun, Yann. Learning Stable Group Invariant Representations with Convolutional Networks. In International Conference on Learning Representations (ICLR), January 2013.
6. Cohen, T. and Welling, M. Learning the Irreducible Representations of Commutative Lie Groups. In International Conference on Machine Learning (ICML), volume 32, 2014.
7. Duchi, John, Hazan, Elad, and Singer, Yoram. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. Journal of Machine Learning Research, 12(Jul):2121–2159, 2011.
8. Gens, Robert and Domingos, Pedro. Deep Symmetry Networks. In Advances in neural information processing systems, 2014.
9. Henriques, Joao F., Martins, Pedro, Caseiro, Rui, and Batista, Jorge. Fast Training of Pose Detectors in the Fourier Domain. In Advances in neural information processing systems, 2014.
10. Hinton, GE, Krizhevsky, A, and Wang, SD. Transforming auto-encoders. ICANN-11: International Conference on Artificial Neural Networks, Helsinki, 2011.
11. Kanatani, K. Group Theoretical Methods in Image Understanding. Springer-Verlag New York, Inc., Secaucus, NJ, USA, 1990. ISBN 0387512535.
12. Kazhdan, Michael, Funkhouser, Thomas, and Rusinkiewicz, Szymon. Rotation invariant spherical harmonic representation of 3D shape descriptors. In Eurographics Symposium on Geometry Processing, 2003.
13. LeCun, Y. and Bottou, L. Learning methods for generic object recognition with invariance to pose and lighting. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2:97–104, 2004. doi: 10.1109/CVPR.2004. 1315150.
14. Mallat, Stephane. Group Invariant Scattering. Communications in Pure and Applied Mathematics, 65(10):1331–1398, 2012.
15. Memisevic, R. On multi-view feature learning. International Conference on Machine Learning, 2012.
16. Miao, X. and Rao, R. P. N. Learning the Lie groups of visual invariance. Neural computation, 19 (10):2665–93, October 2007.
17. Michalski, Vincent, Memisevic, Roland, and Konda, K. Modeling Deep Temporal Dependencies with Recurrent Grammar Cells. In Advances in neural information processing systems, pp. 1–9, 2014.
18. Pinchon, Didier and Hoggan, Philip E. Rotation matrices for real spherical harmonics: general rotations of atomic orbitals in space-fixed axes. Journal of Physics A: Mathematical and Theoretical, 40(7):1597–1610, February 2007. ISSN 1751-8113.
19. Rao, R. P. N. and Ruderman, D. L. Learning Lie groups for invariant visual perception. Advances in neural information processing systems, 816:810–816, 1999.
20. Skibbe, Henrik, Wang, Qing, and Reisert, Marco. Fast computation of 3d spherical fourier harmonic descriptors - a complete orthonormal basis for a rotational invariant representation of three-dimensional objects. In IEEE International Workshop on 3-D Digital Imaging and Modeling (3DIM 2009), in conjunction with the ICCV 2009, pp. 1863-1869, 2009.
21. Soatto, Stefano. Steps Toward a Theory of Visual Information: Active Perception, Signal-to-Symbol Conversion and the Interplay Between Sensing and Control. CoRR, abs/1110.2, 2012.
22. Sohl-Dickstein, J., Wang, J. C., and Olshausen, B. A. An unsupervised algorithm for learning lie group transformations. arXiv preprint, 2010.
23. Sugiura, Mitsuo. Unitary Representations and Harmonic Analysis. John Wiley & Sons, New York, London, Sydney, Toronto, 2nd edition, 1990.
24. Wang, CM, Shol-Dickstein, J, Tosic, Ivana, and Olshausen, Bruno A. Lie Group Transformation Models for Predictive Video Coding. Data Compression Conference, pp. 83–92, 2011.
25. Wigner, E. P. Group Theory and Its Application to the Quantum Mechanics of Atomic Spectra, 1959. ISSN 00029505.