{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T10:02:50Z","timestamp":1774951370834,"version":"3.50.1"},"reference-count":63,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"ANR\n              https:\/\/ror.org\/00rbzpz17","doi-asserted-by":"publisher","award":["ANR-20-CE23-0021"],"award-info":[{"award-number":["ANR-20-CE23-0021"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"French government","doi-asserted-by":"publisher","award":["AMX-21-RID-025"],"award-info":[{"award-number":["AMX-21-RID-025"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Vision"],"abstract":"<jats:p>From falcons spotting prey to humans recognizing faces, the ability to rapidly process visual information depends on a foveated retinal organization that provides high-acuity central vision while preserving low-resolution peripheral vision. This organization is conserved along early visual pathways, yet remains under-explored in machine learning. Here, we examine the impact of embedding a foveated retinotopic transformation as a preprocessing layer on convolutional neural networks (CNNs) for image classification. By applying a log-polar mapping to off-the-shelf models and retraining them, we achieve comparable accuracy while improving robustness to scale and rotation. We demonstrate that this architecture is highly sensitive to shifts in the fixation point and that this sensitivity provides an effective proxy for defining saliency maps that facilitate object localization. Our results demonstrate that foveated retinotopy encodes prior geometric knowledge, providing a solution for visual searches and a meaningful classification robustness and localization trade-off. These findings provides a proof of concept in order to connect principles of biological vision with artificial networks, suggesting new, robust and efficient approaches for computer vision systems.<\/jats:p>","DOI":"10.3390\/vision10020017","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:40:52Z","timestamp":1774878052000},"page":"17","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Foveated Retinotopy Improves Classification and Localization in Convolutional Neural Networks"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9238-6654","authenticated-orcid":false,"given":"Jean-Nicolas","family":"J\u00e9r\u00e9mie","sequence":"first","affiliation":[{"name":"Institut de Neurosciences de la Timone, Aix-Marseille Universit\u00e9, CNRS UMR 7289, 13005 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6596-8168","authenticated-orcid":false,"given":"Emmanuel","family":"Dauc\u00e9","sequence":"additional","affiliation":[{"name":"Institut de Neurosciences de la Timone, Aix-Marseille Universit\u00e9, CNRS UMR 7289, 13005 Marseille, France"},{"name":"Ecole Centrale M\u00e9diterran\u00e9e, Technop\u00f4le Ch\u00e2teau-Gombert, 13013 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9536-010X","authenticated-orcid":false,"given":"Laurent U.","family":"Perrinet","sequence":"additional","affiliation":[{"name":"Institut de Neurosciences de la Timone, Aix-Marseille Universit\u00e9, CNRS UMR 7289, 13005 Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mitkus, M., Potier, S., Martin, G.R., Duriez, O., and Kelber, A. (2018). Raptor Vision. Oxford Research Encyclopedia of Neuroscience, Oxford University Press.","DOI":"10.1093\/acrefore\/9780190264086.013.232"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1111\/cxo.12823","article-title":"Scene through the Eyes of an Apex Predator: A Comparative Analysis of the Shark Visual System","volume":"101","author":"Collin","year":"2018","journal-title":"Clin. Exp. Optom."},{"key":"ref_3","unstructured":"Polyak, S. (1941). The Retina: The Anatomy and the Histology of the Retina in Man, Ape, and Monkey, Including the Consideration of Visual Functions, the History of Physiological Optics, and the Histological Laboratory Technique, University of Chicago Press."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/0042-6989(74)90049-2","article-title":"A Chart Demonstrating Variations in Acuity with Retinal Position","volume":"14","author":"Anstis","year":"1974","journal-title":"Vis. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1016\/S0896-6273(00)80659-5","article-title":"The Retinotopy of Visual Spatial Attention","volume":"21","author":"Tootell","year":"1998","journal-title":"Neuron"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1167\/3.10.1","article-title":"Visual Field Representations and Locations of Visual Areas V1\/2\/3 in Human Visual Cortex","volume":"3","author":"Dougherty","year":"2003","journal-title":"J. Vis."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1016\/j.neuron.2016.07.015","article-title":"Efficient Receptive Field Tiling in Primate V1","volume":"91","author":"Nauhaus","year":"2016","journal-title":"Neuron"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"10654","DOI":"10.1523\/JNEUROSCI.2525-08.2008","article-title":"The Native Coordinate System of Spatial Attention Is Retinotopic","volume":"28","author":"Golomb","year":"2008","journal-title":"J. Neurosci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1038\/s41562-025-02220-7","article-title":"End-to-End Topographic Networks as Models of Cortical Map Formation and Human Visual Behaviour","volume":"9","author":"Lu","year":"2023","journal-title":"Nat. Hum. Behav."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/S0361-9230(97)00095-6","article-title":"Are Topographic Maps Fundamental to Sensory Processing?","volume":"44","author":"Weinberg","year":"1997","journal-title":"Brain Res. Bull."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"R1185","DOI":"10.1016\/j.cub.2024.10.057","article-title":"Building egocentric models of local space from retinal input","volume":"34","author":"Martins","year":"2024","journal-title":"Curr. Biol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1126\/science.171.3968.308","article-title":"Scanpaths in Eye Movements during Pattern Perception","volume":"171","author":"Noton","year":"1971","journal-title":"Science"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/35058500","article-title":"Computational modelling of visual attention","volume":"2","author":"Itti","year":"2001","journal-title":"Nat. Rev. Neurosci."},{"key":"ref_14","first-page":"52","article-title":"Eye Movements during the Examination of Complicated Objects","volume":"6","author":"Yarbus","year":"1961","journal-title":"Biofizika"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1167\/7.14.16","article-title":"Task and Context Determine Where You Look","volume":"7","author":"Rothkopf","year":"2016","journal-title":"J. Vis."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1167\/jov.20.8.22","article-title":"A Dual Foveal-Peripheral Visual Processing Model Implements Efficient Saccade Selection","volume":"20","author":"Albiges","year":"2020","journal-title":"J. Vis."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Verbelen, T., Lanillos, P., Buckley, C.L., and De Boom, C. (2020). Visual Search as Active Inference. Proceedings of the Active Inference, Springer International Publishing.","DOI":"10.1007\/978-3-030-64919-7"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dabane, G., Perrinet, L.U., and Dauc\u00e9, E. (2022). What You See Is What You Transform: Foveated Spatial Transformers as a Bio-Inspired Attention Mechanism. Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN), IEEE.","DOI":"10.1109\/IJCNN55064.2022.9892313"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1016\/0146-664X(80)90026-X","article-title":"An Anthropomorphic Retina-like Structure for Scene Analysis","volume":"14","author":"Sandini","year":"1980","journal-title":"Comput. Graph. Image Process."},{"key":"ref_20","unstructured":"Araujo, H., and Dias, J. (1997). An Introduction to the Log-Polar Mapping. Proceedings II Workshop on Cybernetic Vision, IEEE Computer Society Press."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"192656","DOI":"10.1109\/ACCESS.2024.3519035","article-title":"A 128 \u00d7 128 Electronically Multi-Foveated Dynamic Vision Sensor with Real-Time Resolution Reconfiguration","volume":"12","author":"Faramarzi","year":"2024","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Sarvaiya, J.N., Patnaik, S., and Bombaywala, S. (2009). Image Registration Using Log-Polar Transform and Phase Correlation. Proceedings of the IEEE Region 10 Annual International Conference, IEEE. Proceedings\/TENCON.","DOI":"10.1109\/TENCON.2009.5396234"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Maiello, G., Chessa, M., Bex, P.J., and Solari, F. (2020). Near-Optimal Combination of Disparity across a Log-Polar Scaled Visual Field. PLoS Comput. Biol., 16.","DOI":"10.1371\/journal.pcbi.1007699"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Palander, K., and Brandt, S.S. (2008). Epipolar geometry and log-polar transform in wide baseline stereo matching. Proceedings of the 2008 19th International Conference on Pattern Recognition, IEEE.","DOI":"10.1109\/ICPR.2008.4761515"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.robot.2009.10.002","article-title":"A Review of Log-Polar Imaging for Visual Perception in Robotics","volume":"58","author":"Bernardino","year":"2010","journal-title":"Robot. Auton. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s11554-012-0281-6","article-title":"Speeding up the Log-Polar Transform with Inexpensive Parallel Hardware: Graphics Units and Multi-Core Architectures","volume":"10","author":"Antonelli","year":"2015","journal-title":"J.-Real-Time Image Process."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"202","DOI":"10.3758\/BF03200774","article-title":"Guided Search 2.0 a Revised Model of Visual Search","volume":"1","author":"Wolfe","year":"1994","journal-title":"Psychon. Bull. Rev."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Cao, J., Bao, C., Hao, Q., Cheng, Y., and Chen, C. (2021). LPNet: Retina Inspired Neural Network for Object Detection and Recognition. Electronics, 10.","DOI":"10.3390\/electronics10222883"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"8980","DOI":"10.1038\/s41598-024-59376-x","article-title":"Convolutional neural networks develop major organizational principles of early visual cortex when enhanced with retinal sampling","volume":"14","author":"Kornemann","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lukanov, H., K\u00f6nig, P., and Pipa, G. (2021). Biologically Inspired Deep Learning Model for Efficient Foveal-Peripheral Vision. Front. Comput. Neurosci., 15.","DOI":"10.3389\/fncom.2021.746204"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kubilius, J., Schrimpf, M., Nayebi, A., Bear, D., Yamins, D.L.K., and DiCarlo, J.J. (2018). CORnet: Modeling the Neural Mechanisms of Core Object Recognition. bioRxiv.","DOI":"10.1101\/408385"},{"key":"ref_34","unstructured":"Bengio, Y., Lee, D.H., Bornschein, J., Mesnard, T., and Lin, Z. (2016). Towards Biologically Plausible Deep Learning. arXiv."},{"key":"ref_35","unstructured":"Huang, S.H., Papernot, N., Goodfellow, I.J., Duan, Y., and Abbeel, P. (2017). Adversarial Attacks on Neural Network Policies. arXiv."},{"key":"ref_36","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I.J., and Fergus, R. (2013). Intriguing properties of neural networks. arXiv."},{"key":"ref_37","unstructured":"Mineault, P., Zanichelli, N., Peng, J.Z., Arkhipov, A., Bingham, E., Jara-Ettinger, J., Mackevicius, E., Marblestone, A., Mattar, M., and Payne, A. (2024). NeuroAI for AI Safety. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Lempitsky, V., Vedaldi, A., and Ulyanov, D. (2018). Deep Image Prior. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00984"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Remmelzwaal, L.A., Mishra, A., and Ellis, G.F.R. (2019). Human eye inspired log-polar pre-processing for neural networks. Proceedings of the 2020 International SAUPEC\/RobMech\/PRASA Conference, IEEE.","DOI":"10.1109\/SAUPEC\/RobMech\/PRASA48453.2020.9041103"},{"key":"ref_40","unstructured":"Kim, J., Jung, W., Kim, H., and Lee, J. (2020). CyCNN: A Rotation Invariant CNN Using Polar Mapping and Cylindrical Convolution Layers. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Esteves, C., Allen-Blanchette, C., Makadia, A., and Daniilidis, K. (2017). Learning SO(3) Equivariant Representations with Spherical CNNs. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-01261-8_4"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Hao, Q., Tao, Y., Cao, J., Tang, M., Cheng, Y., Zhou, D., Ning, Y., Bao, C., and Cui, H. (2021). Retina-like Imaging and Its Applications: A Brief Review. Appl. Sci., 11.","DOI":"10.3390\/app11157058"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Traver, V.J., and Pla, F. (2003). Designing the Lattice for Log-Polar Images. International Conference on Discrete Geometry for Computer Imagery, Springer.","DOI":"10.1007\/978-3-540-39966-7_15"},{"key":"ref_44","unstructured":"Wallach, H., Larochelle, H., Beygelzimer, A., Fox, E., and Garnett, R. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. Advances in Neural Information Processing Systems 32, Curran Associates, Inc."},{"key":"ref_45","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., and Kavukcuoglu, K. (2015). Spatial Transformer Networks. Proceedings of the Advances in Neural Information Processing Systems, NIPS."},{"key":"ref_46","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_47","unstructured":"Yu, H., Xu, Y., Zhang, J., Zhao, W., Guan, Z., and Tao, D. (2021). AP-10K: A Benchmark for Animal Pose Estimation in the Wild. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, Z., Du, M., Yang, F., Zhang, Z., Ding, S., Mardziel, P.P., and Hu, X. (2019). Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE.","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"104101","DOI":"10.1016\/j.cviu.2024.104101","article-title":"Opti-CAM: Optimizing saliency maps for interpretability","volume":"248","author":"Zhang","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1126\/science.1145183","article-title":"Meaning in Visual Search","volume":"187","author":"Potter","year":"1975","journal-title":"Science"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"J\u00e9r\u00e9mie, J.N., and Perrinet, L.U. (2023). Ultrafast Image Categorization in Biology and Neural Models. Vision, 7.","DOI":"10.3390\/vision7020029"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1167\/3.6.5","article-title":"Is It an Animal? Is It a Human Face? Fast Processing in Upright and Inverted Natural Scenes","volume":"3","author":"Rousselet","year":"2003","journal-title":"J. Vis."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1167\/6.10.1","article-title":"Animals Roll around the Clock: The Rotation Invariance of Ultrarapid Visual Processing","volume":"6","author":"Guyonneau","year":"2006","journal-title":"J. Vis."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1109\/TPAMI.2003.1195993","article-title":"Log-polar wavelet energy signatures for rotation and scale invariant texture classification","volume":"25","author":"Pun","year":"2003","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Amorim, M., Bortoloti, F., Ciarelli, P.M., de Oliveira, E., and de Souza, A.F. (2018). Analysing rotation-invariance of a log-polar transformation in convolutional neural networks. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), IEEE.","DOI":"10.1109\/IJCNN.2018.8489295"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Crouzet, S.M. (2011). What Are the Visual Features Underlying Rapid Object Recognition?. Front. Psychol., 2.","DOI":"10.3389\/fpsyg.2011.00326"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"473","DOI":"10.26599\/CVM.2025.9450512","article-title":"Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models","volume":"12","author":"Zhao","year":"2026","journal-title":"Comput. Vis. Media"},{"key":"ref_59","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_60","unstructured":"Dallain, M., Rodriguez, L., Perrinet, L.U., and Miramond, B. (2026). A Saccade-Inspired Approach to Image Classification Using Visiontransformer Attention Maps. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1038\/s41598-019-57261-6","article-title":"Scale and translation-invariance for novel objects in human vision","volume":"10","author":"Han","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_62","first-page":"25164","article-title":"The Functional Specialization of Visual Cortex Emerges from Training Parallel Pathways with Self-Supervised Predictive Learning","volume":"Volume 34","author":"Bakhtiari","year":"2021","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_63","first-page":"28757","article-title":"Your Head Is There to Move You Around: Goal-driven Models of the Primate Dorsal Pathway","volume":"Volume 34","author":"Mineault","year":"2021","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"}],"container-title":["Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2411-5150\/10\/2\/17\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:13:47Z","timestamp":1774948427000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2411-5150\/10\/2\/17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":63,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["vision10020017"],"URL":"https:\/\/doi.org\/10.3390\/vision10020017","relation":{},"ISSN":["2411-5150"],"issn-type":[{"value":"2411-5150","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]}}}