Learning intermediate-level representations of form and motion from natural movies

Neural Computation

Volumn 24, Issue 4, 2012, Pages 827-866

  Cadieu, Charles F ^a   Olshausen, Bruno A ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BIOLOGICAL MODEL; HUMAN; LEARNING; LETTER; METHODOLOGY; MOTION; NERVE CELL; PATTERN RECOGNITION; PHOTOSTIMULATION; PHYSIOLOGY; VISUAL CORTEX;

FORM PERCEPTION; HUMANS; LEARNING; MODELS, NEUROLOGICAL; MOTION; NEURONS; PATTERN RECOGNITION, VISUAL; PHOTIC STIMULATION; VISUAL CORTEX;

INVARIANCE; MOTION PICTURES; TEXTURES;

DYNAMIC COMPONENT; EDGE STRUCTURES; FEATURE REPRESENTATION; IMAGE CONTENT; LOCAL MOTIONS; MOTION STRUCTURE; NATURAL ENVIRONMENTS; SECOND LAYER; VISUAL CORTEXES; VISUAL REPRESENTATIONS;

FACTORIZATION;

EID: 84861163812     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/NECO_a_00247     Document Type: Letter

References (76)

1. Adelson, E. H., & Bergen, J. R. (1985). Spatiotemporal energy models for the perception of motion. Journal of the Optical Society of America, 2(2), 284-299.
2. Albrecht, D. G., & Geisler, W. S. (1991).Motion selectivity and the contrast-response function of simple cells in the visual cortex. Visual Neuroscience, 7(6), 531-546.
3. Barlow, H. B. (1961). Possible principles underlying the transformation of sensory messages. In W. A. Rosenblith (Ed.), Sensory communication (pp. 217-234). Cambridge, MA: MIT Press.
4. Barrow, H. G., & Tenenbaum, J. M. (1978). Recovering intrinsic scene characteristics from images. Menlo Park, CA: Artificial Intelligence Center, SRI International.
5. Bell, A. J., & Sejnowski, T. J. (1997). The independent components of natural images are edge filters. Vision Research, 37, 3327-3338.
6. Berkes, P., Turner, R., & Sahani, M. (2009). A structured model of video reproduces primary visual cortical organisation. PLoS Computational Biology, 5(9), e1000495.
7. Berkes, P., & Wiskott, L. (2005). Slow feature analysis yields a rich repertoire of complex cell properties. Journal of Vision, 5(6), 579-602.
8. Born, R. T., & Bradley, D. C. (2005). Structure and function of visual area MT. Annual Review of Neuroscience, 28, 157-189.
9. Burak, Y., Rokni, U., Meister, M., & Sompolinsky, H. (2010). Bayesian model of dynamic image stabilization in the visual system. Proceedings of the National Academy of Sciences, USA, 107(45), 19525-19530.
10. Cadieu, C. F., & Koepsell, K. (2010a). Modeling image structure with factorized phasecoupled Boltzmann machines. arXiv:1011.4058v1.
11. Cadieu, C. F., & Koepsell, K. (2010b). Phase coupling estimation from multivariate phase statistics. Neural Computation, 22(12), 3107-3126.
12. Cadieu, C. F., & Olshausen, B. A. (2009). Learning transformational invariants from natural movies. In D. Koller, D. Schuurmans, Y. Bengio, & L. Bottou (Eds.), Advances in neural information processing systems, 21 (pp. 209-216). Cambridge, MA: MIT Press.
13. Chen, S. S., & Gopinath, R. A. (2000). Gaussianization. In S. A. Solla, T. K. Leen, & K.-R. M̈ uller (Eds.), Advances in neural information processing systems, 12. Cambridge, MA: MIT Press.
14. Culpepper, B. J., & Olshausen, B. A. (2009). Learning transport operators for image manifolds. In Y. Bengio, D. Schuurmans, J. Lafferty, C.K.I. Williams, & A. Culotta (Eds.), Advances in neural information processing systems, 22. Cambridge, MA: MIT Press.
15. DeAngelis, G. C., Ghose, G. M., Ohzawa, I., & Freeman, R. D. (1999). Functional micro-organization of primary visual cortex: Receptive field analysis of nearby neurons. Journal of Neuroscience, 19(10), 4046-4064.
16. DiCarlo, J. J., & Cox, D. D. (2007). Untangling invariant object recognition. Trends in Cognitive Sciences, 11(8), 333-341.
17. Einhauser, W., Kayser, C., Konig, P., & Kording, K. P. (2002). Learning the invariance properties of complex cells from their responses to natural stimuli. European Journal of Neuroscience, 15(3), 475-486.
18. Field, D. J. (1994). What is the goal of sensory coding? Neural Computation, 6(4), 559-601.
19. Fleet, D. J., & Jepson, A. D. (1990). Computation of component image velocity from local phase information. International Journal of Computer Vision, 5(1), 77-104.
20. Foldiak, P. (1991). Learning invariance from transformation sequences. Neural Computation, 3(2), 194-200.
21. Gibson, J. J. (1983). The senses considered as perceptual systems. Westport, CT: Greenwood Press.
22. Grimes, D. B.,&Rao, R.P.N. (2005). Bilinear sparse coding for invariant vision. Neural Computation, 17(1), 47-73.
23. Heeger, D. J. (1991). Nonlinear model of neural responses in cat visual cortex. In M. Landy & J. A. Movshon (Eds.), Computational models of visual processing (pp. 119-133). Cambridge, MA: MIT Press.
24. Horn, B., & Schunck, B. (1981). Determining optical flow. Artificial Intelligence, 17, 185-203.
25. Hoyer, P. O., & Hyv̈arinen, A. (2002). A multi-layer sparse coding network learns contour coding from natural images. Vision Research, 42(12), 1593-1605.
26. Hubel, D.,&Wiesel, T. (1968). Receptive fields and functional architecture of monkey striate cortex. Journal of Physiology, 195(1), 215-243.
27. Hyv̈arinen, A., Gutmann, M., & Hoyer, P. O. (2005). Statistical model of natural stimuli predicts edge-like pooling of spatial frequency channels in V2. BMC Neuroscience, 6(1), 12.
28. Hyv̈arinen, A., & Hoyer, P. O. (2000). Emergence of phase-and shift-invariant features by decomposition of natural images into independent feature subspaces. Neural Computation, 12(7), 1705-1720.
29. Hyv̈arinen, A., Hoyer, P. O.,&Inki, M. (2001). Topographic independent component analysis. Neural Computation, 13(7), 1527-1558.
30. Hyv̈arinen, A., Hurri, J., & V̈ayrynen, J. (2003). Bubbles: A unifying framework for low-level statistical properties of natural image sequences. Journal of the Optical Society of America A, 20(7), 1237-1252.
31. Jhuang, H., Serre, T., Wolf, L., & Poggio, T. (2007). A biologically inspired system for action recognition. In 11th International Conference on Computer Vision (ICCV) (pp. 1-8). Piscataway, NJ: IEEE.
32. Karklin, Y., & Lewicki, M. S. (2003a). Learning higher-order structures in natural images. Network: Computation in Neural Systems, 14, 483-499.
33. Karklin, Y., & Lewicki, M. S. (2003b). A model for learning variance components of natural images. In S. Becker, S. Thr ̈ un, & K. Obermayer (Eds.), Advances in neural information processing systems, 15 (pp. 1367-1374). Cambridge, MA: MIT Press.
34. Karklin, Y., & Lewicki, M. S. (2005). A hierarchical Bayesian model for learning nonlinear statistical regularities in nonstationary natural signals. Neural Computation, 17(2), 397-423.
35. Karklin, Y., & Lewicki, M. S. (2006). Is early vision optimized for extracting higherorder dependencies? In Y. Weiss, B. Scḧolkopf, & J. Platt (Eds.), Advances in neural information processing systems, 18. Cambridge, MA: MIT Press.
36. Karklin, Y.,&Lewicki, M. S. (2008). Emergence of complex cell properties by learning to generalize in natural scenes. Nature, 457(7225), 83-86.
37. Kobatake, E., & Tanaka, K. (1994). Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex. Journal of Neurophysiology, 71(3), 856-867.
38. Koenderink, J. J., & Van Doorn, A. J. (1997). The generic bilinear calibrationestimation problem. International Journal of Computer Vision, 23(3), 217-234.
39. Koster, U., & Hyv̈arinen, A. (2007). A two-layer ICA-like model estimated by score matching. Lecture Notes in Computer Science, 4669, 798-807.
40. LeCun, Y., Huang, F. J., & Bottou, L. (2004). Learning methods for generic object recognition with invariance to pose and lighting. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 97-104). Washington, DC: IEEE Computer Society.
41. Lee, H., Ekanadham, C., & Ng, A. (2007). Sparse deep belief net model for visual area V2. In J. C. Platt, D. K̈ oller, Y. Singer, & S. Roweis (Eds.), Advances in neural information processing systems, 20. Cambridge, MA: MIT Press.
42. Lyu, S., & Simoncelli, E. P. (2009). Nonlinear extraction of independent components of natural images using radial gaussianization. Neural Computation, 21(6), 1485-1519.
43. Magarey, J., & Kingsbury, N. G. (1998). Motion estimation using a complexvalued wavelet transform. IEEE Transactions on Signal Processing, 46(4), 1069-1084.
44. Memisevic, R.,&Hinton, G. (2007).Unsupervised learning of image transformations. In Proceedings of the IEEEComputer SocietyConference onComputerVision and Pattern Recognition (pp. 1-8). Washington, DC: IEEE Computer Society.
45. Nowlan, S. J., & Sejnowski, T. J. (1995). A selection model for motion processing in area MT of primates. Journal of Neuroscience, 15(2), 1195-1214.
46. Olshausen, B. A. (2002). Probabilisticmodels of perception and brain function. Cambridge, MA: MIT Press.
47. Olshausen, B. A., Anderson, C. H., & Van Essen, D. C. (1993). A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. Journal of Neuroscience, 13(11), 4700-4719.
48. Olshausen, B. A., Cadieu, C. F., &Warland, D. K. (2009). Learning real and complex overcomplete representations fromthe statistics of natural images. In Proceedings of SPIE (Vol. 7446, pp. 74460S-74460S-1D). Bellingham, WA: SPIE.
49. Olshausen, B. A., & Field, D. J. (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381(6583), 607-609.
50. Olshausen, B. A., & Field, D. J. (1997). Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Research, 37(23), 3311-3325.
51. Orban, G. A. (2008). Higher order visual processing in macaque extrastriate cortex. Physiological Reviews, 88(1), 59-89.
52. Pollen, D. A., & Ronner, S. F. (1981). Phase relationships between adjacent simple cells in the visual cortex. Science, 212(4501), 1409-1411.
53. Ranzato, M., & Hinton, G. (2010). Modeling pixel means and covariances using factorized third-order Boltzmann machines. In Proc. of ComputerVision and Pattern Recognition Conference (CVPR 2010).
54. Riesenhuber, M., & Poggio, T. (1999). Hierarchical models of object recognition in cortex. Nature Neuroscience, 2, 1019-1025.
55. Rolls, E. T., & Stringer, S. M. (2007). Invariant globalmotion recognition in the dorsal visual system: A unifying theory. Neural Computation, 19(1), 139-169.
56. Rust, N. C., Mante, V., Simoncelli, E. P., & Movshon, J. A. (2006). How MT cells analyze the motion of visual patterns. Nature Neuroscience, 9(11), 1421-1431.
57. Schwartz, O., Sejnowski, T. J., & Dayan, P. (2006). Soft mixer assignment in a hierarchical generative model of natural scene statistics. Neural Computation, 18, 2680-2718.
58. Schwartz, O., & Simoncelli, E. P. (2001). Natural signal statistics and sensory gain control. Nature Neuroscience, 4(8), 819-825.
59. Serre, T., Wolf, L., Bileschi, S., Riesenhuber, M., & Poggio, T. (2007). Robust object recognition with cortex-like mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29, 411-426.
60. Shan, H., Zhang, L., & Cottrell, G. W. (2007). Recursive ICA. In B. Scḧolkopf, J. Platt, & T. Hoffman (Eds.), Advances in neural information processing systems, 19 (pp. 1273-1280). Cambridge, MA: MIT Press.
61. Simoncelli, E. P. (1993). Distributed analysis and representation of visual motion. Unpublished doctoral dissertation, MIT.
62. Simoncelli, E. P. (1997). Statistical models for images: Compression, restoration and synthesis. In Conference Record of the 31st Asilomar Conference on Signals, Systems and Computers (Vol. 1, pp. 673-678). Piscataway, NJ: IEEE.
63. Simoncelli, E. P., & Heeger, D. J. (1998). A model of neuronal responses in visual area MT. Vision Research, 38(5), 743-761.
64. Sinz, F., & Bethge, M. (2008). The conjoint effect of divisive normalization and orientation selectivity on redundancy reduction in natural images. In Frontiers in Computational Neuroscience. Conference Abstract: Bernstein Symposium. doi:10.3389/conf.neuro.10.2008.01.116.
65. Suchow, J. W., & Alvarez, G. A. (2011). Motion silences awareness of visual change. Current Biology, 21, 140-143.
66. Tenenbaum, J., & Freeman, W. (2000). Separating style and content with bilinear models. Neural Computation, 12(6), 1247-1283.
67. Tomasi, C., & Kanade, T. (1992). Shape and motion from image streams under orthography: a factorization method. International Journal of Computer Vision, 9(2), 137-154.
68. Tsunoda, K., Yamane, Y., Nishizaki, M., & Tanifuji, M. (2001). Complex objects are represented in macaque inferotemporal cortex by the combination of feature columns. Nature Neuroscience, 4(8), 832-838.
69. Ullman, S. (2000). High-level vision: Object recognition and visual cognition. Cambridge, MA: MIT Press.
70. Van Hateren, J. H., & Van der Schaaf, A. (1998). Independent component filters of natural images compared with simple cells in primary visual cortex. Proceedings of the Royal Society B: Biological Sciences, 265(1394), 359-366.
71. Wallis, G., & Rolls, E. T. (1997). Invariant face and object recognition in the visual system. Progress in Neurobiology, 51(2), 167-194.
72. Wegmann, B., & Zetzsche, C. (1990). Statistical dependence between orientation filter outputs used in a human-vision-based image code. In Proceedings of SPIE (Vol. 1360, p. 909). Bellingham, WA: SPIE.
73. Wiskott, L., & Sejnowski, T. J. (2002). Slow feature analysis: Unsupervised learning of invariances. Neural Computation, 14(4), 715-770.
74. Yamane, Y., Carlson, E. T., Bowman, K. C., Wang, Z., & Connor, C. E. (2008). A neural code for three-dimensional object shape in macaque inferotemporal cortex. Nature Neuroscience, 11(11), 1352-1360.
75. Zetzsche, C., Krieger, G., & Wegmann, B. (1999). The atoms of vision: Cartesian or polar? Journal of the Optical Society of America A, 16(7), 1554-1565.
76. Zhang, K., Sereno, M. I., & Sereno, M. E. (1993). Emergence of position-independent detectors of sense of rotation and dilation with Hebbian learning: An analysis. Neural Computation, 5(4), 597-612.