Abstract
Recurrent connections in the visual cortex are thought to aid object recognition when part of the stimulus is occluded. Here we investigate if and how recurrent connections in artificial neural networks similarly aid object recognition. We systematically test and compare architectures comprised of bottom-up (B), lateral (L) and top-down (T) connections. Performance is evaluated on a novel stereoscopic occluded object recognition dataset. The task consists of recognizing one target digit occluded by multiple occluder digits in a pseudo-3D environment. We find that recurrent models perform significantly better than their feedforward counterparts, which were matched in parametric complexity. Furthermore, we analyze how the network’s representation of the stimuli evolves over time due to recurrent connections. We show that the recurrent connections tend to move the network’s representation of an occluded digit towards its un-occluded version. Our results suggest that both the brain and artificial neural networks can exploit recurrent connectivity to aid occluded object recognition.
This work was supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement \(\text {N}^{\underline{{\text {o}}}}\) 713010 (GOAL-Robots, Goal-based Open-ended Autonomous Learning Robots).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adesnik, H., Scanziani, M.: Lateral competition for cortical space by layer-specific horizontal circuits. Nature 464(7292), 1155 (2010). https://doi.org/10.1038/nature08935
Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Royal Stat. Soc. Ser. B (Methodol.) 57(1), 289–300 (1995). https://doi.org/10.1111/j.2517-6161.1995.tb02031.x
Brincat, S.L., Connor, C.E.: Dynamic shape synthesis in posterior inferotemporal cortex. Neuron 49(1), 17–24 (2006). https://doi.org/10.1016/j.neuron.2005.11.026
Cichy, R.M., Pantazis, D., Oliva, A.: Resolving human object recognition in space and time. Nat. Neurosci. 17(3), 455 (2014). https://doi.org/10.1038/nn.3635
DiCarlo, J.J., Zoccolan, D., Rust, N.C.: How does the brain solve visual object recognition? Neuron 73(3), 415–434 (2012). https://doi.org/10.1016/j.neuron.2012.01.010
Dietterich, T.G.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput. 10(7), 1895–1923 (1998). https://doi.org/10.1162/089976698300017197
Felleman, D.J., Van Essen, D.C.: Distributed hierarchical processing in the primate cerebral cortex. Cereb. Cortex 1(1), 1–47 (1991). https://doi.org/10.1093/cercor/1.1.1
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456 (2015)
Isik, L., Meyers, E.M., Leibo, J.Z., Poggio, T.: The dynamics of invariant object recognition in the human visual system. J. Neurophysiol. 111(1), 91–102 (2014). https://doi.org/10.1152/jn.00394.2013
Johnson, J.S., Olshausen, B.A.: The recognition of partially visible natural objects in the presence and absence of their occluders. Vision. Res. 45(25), 3262–3276 (2005). https://doi.org/10.1016/j.visres.2005.06.007
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436 (2015). https://doi.org/10.1038/nature14539
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998). https://doi.org/10.1109/5.726791
Liang, M., Hu, X.: Recurrent convolutional neural network for object recognition. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3367–3375 (2015)
Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)
McNemar, Q.: Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika 12(2), 153–157 (1947). https://doi.org/10.1007/BF02295996
O’Reilly, R.C., Wyatte, D., Herd, S., Mingus, B., Jilk, D.J.: Recurrent processing during object recognition. Front. Psychol. 4, 124 (2013). https://doi.org/10.3389/fpsyg.2013.00124
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2(11), 1019–1025 (1999). https://doi.org/10.1038/14819
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533 (1986). https://doi.org/10.1038/323533a0
Serre, T., Oliva, A., Poggio, T.: A feedforward architecture accounts for rapidcategorization. Proc. Natl. Acad. Sci. 104(15), 6424–6429 (2007). https://doi.org/10.1073/pnas.0700622104
Spoerer, C.J., McClure, P., Kriegeskorte, N.: Recurrent convolutional neural networks: a better model of biological object recognition. Front. Psychol. 8, 1551 (2017). https://doi.org/10.3389/fpsyg.2017.01551
Sporns, O., Zwi, J.D.: The small world of the cerebral cortex. Neuroinformatics 2(2), 145–162 (2004). https://doi.org/10.1385/NI:2:2:145
Tang, H., et al.: Spatiotemporal dynamics underlying object completion in human ventral visual cortex. Neuron 83(3), 736–748 (2014). https://doi.org/10.1016/j.neuron.2014.06.017
Thorpe, S., Fize, D., Marlot, C.: Speed of processing in the human visual system. Nature 381(6582), 520–522 (1996). https://doi.org/10.1038/381520a0
Wyatte, D., Curran, T., O’Reilly, R.: The limits of feedforward vision: recurrent processing promotes robust object recognition when objects are degraded. J. Cogn. Neurosci. 24(11), 2248–2261 (2012). https://doi.org/10.1162/jocn_a_00282
Zeiler, M.D., Krishnan, D., Taylor, G.W., Fergus, R.: Deconvolutional networks. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2528–2535. IEEE (2010). https://doi.org/10.1109/CVPR.2010.5539957
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ernst, M.R., Triesch, J., Burwick, T. (2019). Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing. ICANN 2019. Lecture Notes in Computer Science(), vol 11729. Springer, Cham. https://doi.org/10.1007/978-3-030-30508-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-30508-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30507-9
Online ISBN: 978-3-030-30508-6
eBook Packages: Computer ScienceComputer Science (R0)