Abstract
Canonical vision models of the retina-to-V1 cortex pathway consist of cascades of several Linear+Nonlinear layers. In this setting, parameter tuning is the key to obtain a sensible behavior when putting all these multiple layers to work together. Conventional tuning of these neural models very much depends on the explicit computation of the derivatives of the response with regard to the parameters. And, in general, this is not an easy task. Automatic differentiation is a tool developed by the deep learning community to solve similar problems without the need of explicit computation of the analytic derivatives. Therefore, implementations of canonical visual neuroscience models that are ready to be used in an automatic differentiation environment are extremely needed nowadays. In this work we introduce a Python implementation of a standard multi-layer model for the retina-to-V1 pathway. Results show that the proposed default parameters reproduce image distortion psychophysics. More interestingly, given the python implementation, the parameters of this visual model are ready to be optimized with automatic differentiation tools for alternative goals.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ballé, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: 5th International Conference on Learning Representations, ICLR 2017 (2017)
Baydin, A., Pearlmutter, B., Radul, A., Siskind, J.: Automatic differentiation in machine learning: a survey. CoRR abs/1502.05767 (2015). http://arxiv.org/abs/1502.05767
Cai, D., DeAngelis, G., Freeman, R.: Spatiotemporal receptive field organization in the LGN of cats and kittens. J. Neurophysiol. 78(2), 1045–1061 (1997)
Campbell, F., Robson, J.: Application of Fourier analysis to the visibility of gratings. J. Physiol. 197, 551–566 (1968)
Capilla, P., Malo, J., Luque, M., Artigas, J.: Colour representation spaces at different physiological levels: a comparative analysis. J. Opt. 29(5), 324 (1998)
Carandini, M., Heeger, D.: Summation and division by neurons in visual cortex. Science 264(5163), 1333–1336 (1994)
Carandini, M., Heeger, D.J.: Normalization as a canonical neural computation. Nat. Rev. Neurosci. 13(1), 51–62 (2012)
Fairchild, M.: Color Appearance Models. The Wiley-IS&T Series in Imaging Science and Technology, Wiley, Sussex, UK (2013)
Gardner, J., Sun, P., Waggoner, R., Ueno, K., Tanaka, K., Cheng, K.: Contrast adaptation and representation in human early visual cortex. Neuron 47, 607–20 (2005). https://doi.org/10.1016/j.neuron.2005.07.016
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style (2015). http://arxiv.org/abs/1508.06576
Gomez-Villa, A., Bertalmio, M., Malo, J.: Visual information flow in Wilson-Cowan networks. J. Neurophysiol. (2020). https://doi.org/10.1152/jn.0487.2019
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge, MA (2016). http://www.deeplearningbook.org
Günthner, M.F., et al.: Learning divisive normalization in primary visual cortex. bioRxiv (2019). https://doi.org/10.1101/767285
Heeger, D.J.: Normalization of cell responses in cat striate cortex. Vis. Neurosci. 9(2), 181–197 (1992)
Hepburn, A., Laparra, V., Malo, J., McConville, R., Santos, R.: PerceptNet: a human visual system inspired neural net for estimating perceptual distance. In: Proceedings of IEEE ICIP (2020). https://arxiv.org/abs/1910.12548
Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: 25th Neural Information Processing System, NIPS 2012, pp. 1097–1105, Curran Associates Inc., USA (2012)
Laparra, V., Berardino, A., Balle, J., Simoncelli, E.: Perceptually optimized image rendering. JOSA A 34(9), 1511–1525 (2017)
Laparra, V., Muñoz-MarÃ, J., Malo, J.: Divisive normalization image quality metric revisited. JOSA A 27(4), 852–864 (2010)
Malo, J., Simoncelli, E.: Geometrical and statistical properties of vision models obtained via maximum differentiation. In: SPIE Electronic Imaging, pp. 93940L–93940L. International Society for Optics and Photonics (2015)
Martinez, M., BertalmÃo, M., Malo, J.: In praise of artifice reloaded: caution with natural image databases in modeling vision. Front. Neurosci. (2019). https://doi.org/10.3389/fnins.2019.00008
Martinez-Garcia, M., Cyriac, P., Batard, T., BertalmÃo, M., Malo, J.: Derivatives and inverse of cascaded linear+nonlinear neural models. PLOS ONE 13(10), 1–49 (2018). https://doi.org/10.1371/journal.pone.0201326
Mullen, K.T.: The CSF of human colour vision to red-green and yellow-blue chromatic gratings. J. Physiol. 359, 381–400 (1985)
Pestilli, F., Carrasco, M., Heeger, D., Gardner, J.: Attentional enhancement via selection and pooling of early sensory responses in human visual cortex. Neuron 72, 832–46 (2011). https://doi.org/10.1016/j.neuron.2011.09.025
Ponomarenko, N., Carli, M., Lukin, V., Egiazarian, K., Astola, J., Battisti, F.: Color image database for evaluation of image quality metrics. In: Proceedings of International Workshop on Multimedia Signal Processing, pp. 403–408 (2008)
Ringach, D.: Spatial structure and symmetry of simple-cell receptive fields in macaque primary visual cortex. J. Neurophysiol. 88(1), 455–463 (2002)
Schutt, H.H., Wichmann, F.A.: An image-computable psychophysical spatial vision model. J. Vis. 17(12), 12 (2017). https://doi.org/10.1167/17.12.12
Shapley, R., Hawken, M.: Color in the cortex: single- and double-opponent cells. Vis. Res. 51(7), 701–717 (2011)
Simoncelli, E.P., Freeman, W.T., Adelson, E.H., Heeger, D.J.: Shiftable multi-scale transforms. IEEE Trans. Inf. Theory 38(2), 587–607 (1992). https://doi.org/10.1109/18.119725. Special Issue on Wavelets
Stockman, A., Brainard, D.: Color vision mechanisms. In: OSA Handbook of Optics, 3rd edn., pp. 147–152. McGraw-Hill, NY (2010)
Stockman, A., Sharpe, L.: The spectral sensitivities of the middle- and long-wavelength-sensitive cones derived from measurements in observers of known genotype. Vis. Res. 40(13), 1711–1737 (2000)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Proc. 13(4), 600–612 (2004)
Wang, Z., Simoncelli, E.: SSIM results in TID2008 (2011). http://cns.nyu.edu/ lcv/ssim
Wang, Z., Simoncelli, E.P.: Maximum differentiation (MAD) competition: a methodology for comparing computational models of perceptual quantities. J. Vis. 8(12), 8 (2008)
Watson, A.B., Malo, J.: Video quality measures based on the standard spatial observer. In: 2002 International Conference on Image Processing, Proceedings, vol. 3, pp. III-41. IEEE (2002)
Watson, A.B., Ramirez, C.: A standard observer for spatial vision based on modelfest dataset (1999)
Watson, A.B., Solomon, J.A.: Model of visual contrast gain control and pattern masking. JOSA A 14(9), 2379–2391 (1997)
Whitman, A., Obituary, van der Rohe, M.: Leader of Modern Architecture. The New York Times (1969)
Wilson, H.R., Cowan, J.D.: A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue. Kybernetik 13(2), 55–80 (1973)
Zenger-Landolt, B., Heeger, D.: Response suppression in v1 agrees with psychophysics of surround masking. J. Neurosci. Off. J. Soc. Neurosci. 23, 6884–6893 (2003). https://doi.org/10.1523/JNEUROSCI.23-17-06884.2003
Zhang, R., Isola, P., Efros, A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of IEEE CVPR, pp. 586–595 (2018)
Acknowledgment
Thanks to all of the open-source contributors in the open-source community. We would like to thank the reviewers for their thoughtful comments and efforts towards improving our manuscript. Finally, we also want to thank all of the doctors in the world who keep all of us safe during the COVID 19 epidemic.
This work was partially funded by the Spanish Government through the grant MINECO DPI2017-89867 and by the Generalitat Valenciana through the grant GrisoliaP/2019/035.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Q., Malo, J. (2020). Canonical Retina-to-Cortex Vision Model Ready for Automatic Differentiation. In: Mahmud, M., Vassanelli, S., Kaiser, M.S., Zhong, N. (eds) Brain Informatics. BI 2020. Lecture Notes in Computer Science(), vol 12241. Springer, Cham. https://doi.org/10.1007/978-3-030-59277-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-59277-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59276-9
Online ISBN: 978-3-030-59277-6
eBook Packages: Computer ScienceComputer Science (R0)