Abstract
We have developed a neural network model capable of performing visual binding inspired by neuronal circuitry in the optic glomeruli of flies: a brain area that lies just downstream of the optic lobes where early visual processing is performed. This visual binding model is able to detect objects in dynamic image sequences and bind together their respective characteristic visual features—such as color, motion, and orientation—by taking advantage of their common temporal fluctuations. Visual binding is represented in the form of an inhibitory weight matrix which learns over time which features originate from a given visual object. In the present work, we show that information represented implicitly in this weight matrix can be used to explicitly count the number of objects present in the visual image, to enumerate their specific visual characteristics, and even to create an enhanced image in which one particular object is emphasized over others, thus implementing a simple form of visual attention. Further, we present a detailed analysis which reveals the function and theoretical limitations of the visual binding network and in this context describe a novel network learning rule which is optimized for visual binding.
Similar content being viewed by others
References
Bell AJ, Sejnowski TJ (1995) An information-maximization approach to blind separation and blind deconvolution. Neural Comput 7(6):1129–1159
Blakemore C, Tobin EA (1972) Lateral inhibition between orientation detectors in the cat’s visual cortex. Exp Brain Res 15(4):439–440
Brooks RA (1991) Intelligence without representation. Artif Intell 47(1):139–159
Brooks RA (1995) Intelligence without reason. Building embodied, situated agents, The artificial life route to artificial intelligence, pp 25–81
Cichocki A, Bogner RE, Moszczyński L, Pope K (1997) Modified Herault–Jutten algorithms for blind separation of sources. Digit Signal Process 7(2):80–93
Comon P (1994) Independent component analysis, A new concept? Signal Process 36(3):287–314
DiCarlo JJ, Zoccolan D, Rust NC (2012) How does the brain solve visual object recognition? Neuron 73(3):415–434
Douglas RJ, Martin KA, Whitteridge D (1989) A canonical microcircuit for neocortex. Neural Comput 1(4):480–488
Guo L, Garland M (2006) The use of entropy minimization for the solution of blind source separation problems in image analysis. Pattern Recogn 39(6):1066–1073
Hassenstein B, Reichardt W (1956) Systemtheoretische Analyse der Zeit-, Reihenfolgen- und Vorzeichenauswertung bei der Bewegungsperzeption des Rüsselkäfers Chlorophanus. Z Naturforsch B 11(9–10):513–524
Hebb DO (1949) The organization of behavior: a neuropsychological theory. Wiley, New York
Herault J, Jutten C (1986) Space or time adaptive signal processing by neural network models. In: AIP conference proceedings, vol 151. Snowbird, UT, pp 206–211
Hopfield JJ (1991) Olfactory computation and object perception. Proc Natl Acad Sci USA 88(15):6462–6466
Hyvärinen A, Oja E (1998) Independent component analysis by general nonlinear Hebbian-like learning rules. Signal Process 64(3):301–313
Itti L, Koch C (2001) Computational modelling of visual attention. Nat Rev Neurosci 2(3):194–203
Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal 20(11):1254–1259
Joho M, Mathis H, Lambert RH (2000) Overdetermined blind source separation: Using more sensors than source signals in a noisy mixture. In: Proceedings international conference on independent component analysis and blind signal separation. Helsinki, Finland, pp 81–86
Jutten C, Herault J (1991) Blind separation of sources, Part I: an adaptive algorithm based on neuromimetic architecture. Signal Process 24(1):1–10
Lee DK, Itti L, Koch C, Braun J (1999) Attention activates winner-take-all competition among visual filters. Nat Neurosci 2(4):375–381
Linster C, Smith BH (1997) A computational model of the response of honey bee antennal lobe circuitry to odor mixtures: overshadowing, blocking and unblocking can arise from lateral inhibition. Behav Brain Res 87(1):1–14
Mach E (1866) Über die physiologische Wirkung räumlich vertheilter Lichtreize (On the physiological effects of spatially distributed light stimuli). Akad der Wiss, Wien, Sitzber, Math-Nat K 54(2):393
Markram H, Lübke J, Frotscher M, Sakmann B (1997) Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs. Science 275(5297):213–215
Moran J, Desimone R (1985) Selective attention gates visual processing in the extrastriate cortex. Science 229(4715):782–784
Mu L, Ito K, Bacon JP, Strausfeld NJ (2012) Optic glomeruli and their inputs in Drosophila share an organizational ground pattern with the antennal lobes. J Neurosci 32(18):6061–6071
Nguyen AP, Spetch ML, Crowder NA, Winship IR, Hurd PL, Wylie DR (2004) A dissociation of motion and spatial-pattern vision in the avian telencephalon: implications for the evolution of visual streams. J Neurosci 24(21):4962–4970
Northcutt BD, Higgins CM (2017) An insect-inspired model for visual binding II: functional analysis and visual attention. In: Review, Biol Cybern
Northcutt BD, Dyhr JP, Higgins CM (2017) An insect-inspired model for visual binding I: learning objects and their characteristics. In: Review, Biol Cybern
Okamura JY, Strausfeld NJ (2007) Visual system of Calliphorid flies: motion- and orientation-sensitive visual interneurons supplying dorsal optic glomeruli. J Comp Neurol 500(1):189–208
Paulk AC, Phillips-Portillo J, Dacks AM, Fellous JM, Gronenberg W (2008) The processing of color, motion, and stimulus timing are anatomically segregated in the bumblebee brain. J Neurosci 28(25):6319–6332
Paulk AC, Dacks AM, Phillips-Portillo J, Fellous JM, Gronenberg W (2009) Visual processing in the central bee brain. J Neurosci 29(32):9987–9999
Rivera-Alvidrez Z, Lin I, Higgins CM (2011) A neuronally based model of contrast gain adaptation in fly motion vision. Vis Neurosci 28(5):419–431
Scholl BJ (2001) Objects and attention: the state of the art. Cognition 80(1):1–46
Shamma SA (1985) Speech processing in the auditory system II: lateral inhibition and the central processing of speech evoked activity in the auditory nerve. J Acoust Soc Am 78(5):1622–1632
Snyder AW (1979) Handbook of sensory physiology, vol VII/6A, chap 5. In: Autrum H (ed) Physics of vision in compound eyes. Springer, Berlin, Heidelberg, pp 225–313
Sorouchyari E (1991) Blind separation of sources. Part III: stability analysis. Signal Process 24(1):21–29
Strausfeld NJ, Okamura JY (2007) Visual system of Calliphorid flies: organization of optic glomeruli and their lobula complex efferents. J Comp Neurol 500(1):166–188
Strausfeld NJ, Sinakevitch I, Okamura JY (2007) Organization of local interneurons in optic glomeruli of the Dipterous visual system and comparisons with the antennal lobes. Dev Neurobiol 67(10):1267–1288
Trentelman H, Stoorvogel AA, Hautus M (2012) Control theory for linear systems. Springer, London
van Santen JPH, Sperling G (1985) Elaborated Reichardt detectors. J Opt Soc Am A 2(5):300–320
von der Malsburg C (1999) The what and why of binding: the modeler’s perspective. Neuron 24(1):95–104
Werner G (2012) From brain states to mental phenomena via phase space transitions and renormalization group transformation: proposal of a theory. Cogn Neurodyn 6(2):199–202
Yang HH, Si A (1997) Adaptive online learning algorithms for blind separation: maximum entropy and minimum mutual information. Neural Comput 9(7):1457–1482
Acknowledgements
The authors would like to thank the Air Force Office of Scientific Research for early support of the modeling research on this project with Grant Number FA9550-07-1-0165, and the Air Force Research Laboratories for supporting this research to maturity with STTR Phase I Award Number FA8651-13-M-0085 and Phase II Award Number FA8651-14-C-0108, both in collaboration with Spectral Imaging Laboratory (Pasadena, CA). We would also like to thank the reviewers, whose input greatly enhanced this manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Northcutt, B.D., Higgins, C.M. An insect-inspired model for visual binding II: functional analysis and visual attention. Biol Cybern 111, 207–227 (2017). https://doi.org/10.1007/s00422-017-0716-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-017-0716-z