{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T10:30:59Z","timestamp":1789900259493,"version":"4.0.1"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003130","name":"Fonds voor Wetenschappelijk Onderzoek","doi-asserted-by":"crossref","award":["11C9124N"],"award-info":[{"award-number":["11C9124N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003130","name":"Fonds voor Wetenschappelijk Onderzoek","doi-asserted-by":"crossref","award":["G073122N"],"award-info":[{"award-number":["G073122N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100011878","name":"Flemish Government","doi-asserted-by":"crossref","award":["METH 1241003"],"award-info":[{"award-number":["METH 1241003"]}],"id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Object recognition requires flexible and robust information processing, especially in view of the challenges posed by naturalistic visual settings. The ventral stream in visual cortex is provided with this robustness by its recurrent connectivity. Recurrent deep neural networks (DNNs) have recently emerged as promising models of the ventral stream, surpassing feedforward DNNs in the ability to account for brain representations. In this study, we asked whether recurrent DNNs could also better account for human behaviour during visual recognition. We assembled a stimulus set that includes manipulations that are often associated with recurrent processing in the literature, like occlusion, partial viewing, clutter, and spatial phase scrambling. We obtained a benchmark dataset from human participants performing a categorisation task on this stimulus set. By applying a wide range of model architectures to the same task, we uncovered a nuanced relationship between recurrence, model size, and performance. First, results show that increases in performance were most strongly linked to increases in model size, with architecture seemingly not playing a role, even for more challenging manipulations. Second, we found larger models to be more consistent with humans on which manipulations they found more difficult, regardless of model architecture. Finally, we found a negative effect of size in matching human confusion matrices in recurrent but not feedforward DNNs. Contrary to previous assumptions, our findings challenge the notion that recurrent models are better models of human recognition behaviour than feedforward models, and emphasise the complexity of incorporating recurrence into computational models.<\/jats:p>","DOI":"10.1038\/s41598-025-20245-w","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:36:27Z","timestamp":1760711787000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Recurrent issues with deep neural network models of visual recognition"],"prefix":"10.1038","volume":"15","author":[{"given":"Timothee","family":"Maniquet","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans Op","family":"de Beeck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea Ivan","family":"Costantino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"20245_CR1","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.tics.2012.10.011","volume":"17","author":"DJ Kravitz","year":"2013","unstructured":"Kravitz, D. J., Saleem, K. S., Baker, C. I., Ungerleider, L. G. & Mishkin, M. The ventral visual pathway: An expanded neural framework for the processing of object quality. Trends Cognit. Sci. 17, 26\u201349 (2013).","journal-title":"Trends Cognit. Sci."},{"key":"20245_CR2","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1038\/nrn3747","volume":"15","author":"K Grill-Spector","year":"2014","unstructured":"Grill-Spector, K. & Weiner, K. S. The functional architecture of the ventral temporal cortex and its role in categorization. Nat. Rev. Neurosci. 15, 536\u2013548 (2014).","journal-title":"Nat. Rev. Neurosci."},{"key":"20245_CR3","doi-asserted-by":"crossref","unstructured":"Bracci, S. & Op de Beeck, H. P. Understanding human object vision: A picture is worth a thousand representations. Ann. Rev. Psychol. 74, 113\u2013135 (2023).","DOI":"10.1146\/annurev-psych-032720-041031"},{"key":"20245_CR4","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1002\/cne.902440405","volume":"244","author":"DC Essen","year":"1986","unstructured":"Essen, D. C., Newsome, W. T., Maunsell, J. H. & Bixby, J. L. The projections from striate cortex (V1) to areas V2 and V3 in the macaque monkey: Asymmetries, areal boundaries, and patchy connections. J. Comp. Neurol. 244, 451\u2013480 (1986).","journal-title":"J. Comp. Neurol."},{"key":"20245_CR5","doi-asserted-by":"crossref","unstructured":"Felleman, D.\u00a0J. & Van Essen, D.\u00a0C. Distributed hierarchical processing in the primate cerebral cortex. Cereb. Cortex (New York, N.Y.: 1991) 1, 1\u201347 (1991 Jan-Feb).","DOI":"10.1093\/cercor\/1.1.1"},{"key":"20245_CR6","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1016\/S0959-4388(98)80042-1","volume":"8","author":"VA Lamme","year":"1998","unstructured":"Lamme, V. A., Sup\u00e8r, H. & Spekreijse, H. Feedforward, horizontal, and feedback processing in the visual cortex. Curr. Opin. Neurobiol. 8, 529\u2013535 (1998).","journal-title":"Curr. Opin. Neurobiol."},{"key":"20245_CR7","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1093\/cercor\/bhm061","volume":"18","author":"LG Ungerleider","year":"2008","unstructured":"Ungerleider, L. G., Galkin, T. W., Desimone, R. & Gattass, R. Cortical connections of area V4 in the Macaque. Cereb. Cortex 18, 477\u2013499 (2008).","journal-title":"Cereb. Cortex"},{"key":"20245_CR8","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1523\/JNEUROSCI.11-01-00168.1991","volume":"11","author":"JS Baizer","year":"1991","unstructured":"Baizer, J. S., Ungerleider, L. G. & Desimone, R. Organization of visual inputs to the inferior temporal and posterior parietal cortex in macaques. J. Neurosci. 11, 168\u2013190 (1991).","journal-title":"J. Neurosci."},{"key":"20245_CR9","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.neuron.2012.01.010","volume":"73","author":"JJ DiCarlo","year":"2012","unstructured":"DiCarlo, J. J., Zoccolan, D. & Rust, N. C. How does the brain solve visual object recognition?. Neuron 73, 415\u2013434 (2012).","journal-title":"Neuron"},{"key":"20245_CR10","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1038\/81479","volume":"3","author":"M Riesenhuber","year":"2000","unstructured":"Riesenhuber, M. & Poggio, T. Models of object recognition. Nat. Neurosci. 3, 1199\u20131204 (2000).","journal-title":"Nat. Neurosci."},{"key":"20245_CR11","doi-asserted-by":"crossref","unstructured":"Riesenhuber, M. Object recognition in cortex: Neural mechanisms, and possible roles for attention. In Neurobiology of Attention. 279\u2013287 (Elsevier, 2005).","DOI":"10.1016\/B978-012375731-9\/50050-1"},{"key":"20245_CR12","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/j.tins.2019.07.005","volume":"42","author":"CM Pennartz","year":"2019","unstructured":"Pennartz, C. M., Dora, S., Muckli, L. & Lorteije, J. A. Towards a unified view on pathways and functions of neural recurrent processing. Trends Neurosci. 42, 589\u2013603 (2019).","journal-title":"Trends Neurosci."},{"key":"20245_CR13","doi-asserted-by":"crossref","unstructured":"Wyatte, D., Jilk, D.\u00a0J. & O\u2019Reilly, R.\u00a0C. Early recurrent feedback facilitates visual object recognition under challenging conditions. Front. Psychol. 5 (2014).","DOI":"10.3389\/fpsyg.2014.00674"},{"key":"20245_CR14","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1016\/S0166-2236(00)01657-X","volume":"23","author":"VA Lamme","year":"2000","unstructured":"Lamme, V. A. & Roelfsema, P. R. The distinct modes of vision offered by feedforward and recurrent processing. Trends Neurosci. 23, 571\u2013579 (2000).","journal-title":"Trends Neurosci."},{"key":"20245_CR15","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1111\/nyas.14320","volume":"1464","author":"G Kreiman","year":"2020","unstructured":"Kreiman, G. & Serre, T. Beyond the feedforward sweep: Feedback computations in the visual cortex. Ann. N. Y. Acad. Sci. 1464, 222\u2013241 (2020).","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"20245_CR16","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1162\/jocn.2007.19.9.1488","volume":"19","author":"JJ Fahrenfort","year":"2007","unstructured":"Fahrenfort, J. J., Scholte, H. S. & Lamme, V. A. F. Masking disrupts reentrant processing in human visual cortex. J. Cognit. Neurosci. 19, 1488\u20131497 (2007).","journal-title":"J. Cognit. Neurosci."},{"key":"20245_CR17","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1162\/089892902320474490","volume":"14","author":"VAF Lamme","year":"2002","unstructured":"Lamme, V. A. F., Zipser, K. & Spekreijse, H. Masking interrupts figure-ground signals in V1. J. Cognit. Neurosci. 14, 1044\u20131053 (2002).","journal-title":"J. Cognit. Neurosci."},{"key":"20245_CR18","doi-asserted-by":"publisher","first-page":"6281","DOI":"10.1523\/JNEUROSCI.2851-20.2021","volume":"41","author":"N Seijdel","year":"2021","unstructured":"Seijdel, N. et al. On the necessity of recurrent processing during object recognition: it depends on the need for scene segmentation. J. Neurosci. 41, 6281\u20136289 (2021).","journal-title":"J. Neurosci."},{"key":"20245_CR19","doi-asserted-by":"publisher","first-page":"e1007001","DOI":"10.1371\/journal.pcbi.1007001","volume":"15","author":"K Rajaei","year":"2019","unstructured":"Rajaei, K., Mohsenzadeh, Y., Ebrahimpour, R. & Khaligh-Razavi, S.-M. Beyond core object recognition: Recurrent processes account for object recognition under occlusion. PLOS Comput. Biol. 15, e1007001 (2019).","journal-title":"PLOS Comput. Biol."},{"key":"20245_CR20","doi-asserted-by":"publisher","first-page":"8835","DOI":"10.1073\/pnas.1719397115","volume":"115","author":"H Tang","year":"2018","unstructured":"Tang, H. et al. Recurrent computations for visual pattern completion. Proc. Natl. Acad. Sci. 115, 8835\u20138840 (2018).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"20245_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42003-023-05042-3","volume":"6","author":"HJ Ladret","year":"2023","unstructured":"Ladret, H. J. et al. Cortical recurrence supports resilience to sensory variance in the primary visual cortex. Commun. Biol. 6, 1\u201313 (2023).","journal-title":"Commun. Biol."},{"key":"20245_CR22","doi-asserted-by":"crossref","unstructured":"Shin, H. et al. Recurrent pattern completion drives the neocortical representation of sensory inference (2023).","DOI":"10.1101\/2023.06.05.543698"},{"key":"20245_CR23","doi-asserted-by":"publisher","first-page":"2121","DOI":"10.1016\/j.cub.2013.09.013","volume":"23","author":"MW Self","year":"2013","unstructured":"Self, M. W., Kerkoerle, T., Sup\u00e8r, H. & Roelfsema, P. R. Distinct roles of the cortical layers of area V1 in figure-ground segregation. Curr. Biol. 23, 2121\u20132129 (2013).","journal-title":"Curr. Biol."},{"key":"20245_CR24","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1162\/neco_a_01072","volume":"30","author":"H Choi","year":"2018","unstructured":"Choi, H., Pasupathy, A. & Shea-Brown, E. Predictive coding in area V4: Dynamic shape discrimination under partial occlusion. Neural Comput. 30, 1209\u20131257 (2018).","journal-title":"Neural Comput."},{"key":"20245_CR25","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.neuron.2017.05.033","volume":"95","author":"PC Klink","year":"2017","unstructured":"Klink, P. C., Dagnino, B., Gariel-Mathis, M.-A. & Roelfsema, P. R. Distinct feedforward and feedback effects of microstimulation in visual cortex reveal neural mechanisms of texture segregation. Neuron 95, 209-220.e3 (2017).","journal-title":"Neuron"},{"key":"20245_CR26","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1146\/annurev-neuro-072116-031418","volume":"40","author":"A Angelucci","year":"2017","unstructured":"Angelucci, A. et al. Circuits and mechanisms for surround modulation in visual cortex. Annu. Rev. Neurosci. 40, 425\u2013451 (2017).","journal-title":"Annu. Rev. Neurosci."},{"key":"20245_CR27","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1073\/pnas.0507062103","volume":"103","author":"M Bar","year":"2006","unstructured":"Bar, M. et al. Top-down facilitation of visual recognition. Proc. Natl. Acad. Sci. 103, 449\u2013454 (2006).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"20245_CR28","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1016\/j.neuroimage.2016.01.006","volume":"128","author":"E Goddard","year":"2016","unstructured":"Goddard, E., Carlson, T. A., Dermody, N. & Woolgar, A. Representational dynamics of object recognition: Feedforward and feedback information flows. NeuroImage 128, 385\u2013397 (2016).","journal-title":"NeuroImage"},{"key":"20245_CR29","doi-asserted-by":"publisher","first-page":"3e1003963","DOI":"10.1371\/journal.pcbi.1003963","volume":"10","author":"CF Cadieu","year":"2014","unstructured":"Cadieu, C. F. et al. Deep neural networks rival the representation of primate IT cortex for core visual object recognition. PLOS Comput. Biol. 10, 3e1003963 (2014).","journal-title":"PLOS Comput. Biol."},{"key":"20245_CR30","doi-asserted-by":"publisher","first-page":"8619","DOI":"10.1073\/pnas.1403112111","volume":"111","author":"DLK Yamins","year":"2014","unstructured":"Yamins, D. L. K. et al. Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proc. Natl. Acad. Sci. 111, 8619\u20138624 (2014).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"20245_CR31","doi-asserted-by":"publisher","first-page":"e1003915","DOI":"10.1371\/journal.pcbi.1003915","volume":"10","author":"S-M Khaligh-Razavi","year":"2014","unstructured":"Khaligh-Razavi, S.-M. & Kriegeskorte, N. Deep supervised, but not unsupervised, models may explain IT cortical representation. PLoS Comput. Biol. 10, e1003915 (2014).","journal-title":"PLoS Comput. Biol."},{"key":"20245_CR32","doi-asserted-by":"publisher","first-page":"974","DOI":"10.1038\/s41593-019-0392-5","volume":"22","author":"K Kar","year":"2019","unstructured":"Kar, K., Kubilius, J., Schmidt, K., Issa, E. B. & DiCarlo, J. J. Evidence that recurrent circuits are critical to the ventral stream\u2019s execution of core object recognition behavior. Nat. Neurosci. 22, 974\u2013983 (2019).","journal-title":"Nat. Neurosci."},{"key":"20245_CR33","doi-asserted-by":"publisher","first-page":"21854","DOI":"10.1073\/pnas.1905544116","volume":"116","author":"TC Kietzmann","year":"2019","unstructured":"Kietzmann, T. C. et al. Recurrence is required to capture the representational dynamics of the human visual system. Proc. Natl. Acad. Sci. 116, 21854\u201321863 (2019).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"20245_CR34","doi-asserted-by":"publisher","first-page":"e1008215","DOI":"10.1371\/journal.pcbi.1008215","volume":"16","author":"CJ Spoerer","year":"2020","unstructured":"Spoerer, C. J., Kietzmann, T. C., Mehrer, J., Charest, I. & Kriegeskorte, N. Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision. PLOS Comput. Biol. 16, e1008215 (2020).","journal-title":"PLOS Comput. Biol."},{"key":"20245_CR35","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.conb.2020.11.009","volume":"65","author":"RS Bergen","year":"2020","unstructured":"Bergen, R. S. & Kriegeskorte, N. Going in circles is the way forward: The role of recurrence in visual inference. Curr. Opin. Neurobiol. 65, 176\u2013193 (2020).","journal-title":"Curr. Opin. Neurobiol."},{"key":"20245_CR36","doi-asserted-by":"crossref","unstructured":"Bowers, J.\u00a0S. et al. Deep Problems with Neural Network Models of Human Vision (2022).","DOI":"10.31234\/osf.io\/5zf4s"},{"key":"20245_CR37","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1146\/annurev-vision-120522-031739","volume":"9","author":"FA Wichmann","year":"2023","unstructured":"Wichmann, F. A. & Geirhos, R. Are deep neural networks adequate behavioral models of human visual perception?. Annu. Rev. Vis. Sci. 9, 501\u2013524 (2023).","journal-title":"Annu. Rev. Vis. Sci."},{"key":"20245_CR38","unstructured":"Geirhos, R. et al. Comparing deep neural networks against humans: Object recognition when the signal gets weaker (2018). arXiv:1706.06969."},{"key":"20245_CR39","unstructured":"Geirhos, R. et al. Generalisation in humans and deep neural networks. arXiv:1808.08750 [cs, q-bio, stat] (2020)."},{"key":"20245_CR40","unstructured":"Geirhos, R. et al. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness (2022). arXiv:1811.12231."},{"key":"20245_CR41","doi-asserted-by":"crossref","unstructured":"O\u2019Reilly, R.\u00a0C., Wyatte, D., Herd, S., Mingus, B. & Jilk, D.\u00a0J. Recurrent processing during object recognition. Front. Psychol. 4 (2013).","DOI":"10.3389\/fpsyg.2013.00124"},{"key":"20245_CR42","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Microsoft COCO: Common objects in context. In Computer Vision\u2014ECCV 2014 (Fleet, D., Pajdla, T., Schiele, B. & Tuytelaars, T. eds.) Lecture Notes in Computer Science. 740\u2013755 (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"20245_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, B. et al. Semantic Understanding of Scenes Through the ADE20K Dataset. arXiv (2018).","DOI":"10.1007\/s11263-018-1140-0"},{"key":"20245_CR44","doi-asserted-by":"publisher","first-page":"18814","DOI":"10.1523\/JNEUROSCI.3128-13.2013","volume":"33","author":"IIA Groen","year":"2013","unstructured":"Groen, I. I. A., Ghebreab, S., Prins, H., Lamme, V. A. F. & Scholte, H. S. From image statistics to scene gist: Evoked neural activity reveals transition from low-level natural image structure to scene category. J. Neurosci. 33, 18814\u201318824 (2013).","journal-title":"J. Neurosci."},{"key":"20245_CR45","doi-asserted-by":"crossref","unstructured":"Kubilius, J. et al. CORnet: Modeling the Neural Mechanisms of Core Object Recognition (2018).","DOI":"10.1101\/408385"},{"key":"20245_CR46","unstructured":"Kubilius, J. et al. Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs (2019). arXiv:1909.06161."},{"key":"20245_CR47","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.3389\/fpsyg.2017.01551","volume":"8","author":"CJ Spoerer","year":"2017","unstructured":"Spoerer, C. J., McClure, P. & Kriegeskorte, N. Recurrent convolutional neural networks: A better model of biological object recognition. Front. Psychol. 8, 1551 (2017).","journal-title":"Front. Psychol."},{"key":"20245_CR48","unstructured":"Thorat, S., Kietzmann, T. & Doerig, A. BLT MiniEcoset CCN23 Weights (2023). https:\/\/osf.io\/pw238\/."},{"key":"20245_CR49","unstructured":"Simonyan, K. & Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition (2015). arXiv:1409.1556."},{"key":"20245_CR50","doi-asserted-by":"crossref","unstructured":"Smith, L.\u00a0N. & Topin, N. Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates (2018). arXiv:1708.07120.","DOI":"10.1117\/12.2520589"},{"key":"20245_CR51","unstructured":"Fastai\/fastai: The fastai deep learning library. https:\/\/github.com\/fastai\/fastai."},{"key":"20245_CR52","doi-asserted-by":"crossref","unstructured":"Smith, L.\u00a0N. Cyclical Learning Rates for Training Neural Networks (2017). arXiv:1506.01186.","DOI":"10.1109\/WACV.2017.58"},{"key":"20245_CR53","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"20245_CR54","unstructured":"Ansel, J. et al. PyTorch 2: Faster machine learning through dynamic python bytecode transformation and graph compilation. In Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2 (ASPLOS \u201924) (ACM, 2024)."},{"key":"20245_CR55","unstructured":"Paszke, A. et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library (2019). arXiv:1912.01703."},{"key":"20245_CR56","unstructured":"Howard, J. et al. Fastai (2018)."},{"key":"20245_CR57","doi-asserted-by":"crossref","unstructured":"Avber\u0161ek, L.\u00a0K., Zeman, A. & Op de Beeck, H. Training for object recognition with increasing spatial frequency: A comparison of deep learning with human vision. J. Vis. 21, 14 (2021).","DOI":"10.1167\/jov.21.10.14"},{"key":"20245_CR58","doi-asserted-by":"crossref","unstructured":"Ghodrati, M., Farzmahdi, A., Rajaei, K., Ebrahimpour, R. & Khaligh-Razavi, S.-M. Feedforward object-vision models only tolerate small image variations compared to human. Front. Comput. Neurosci. 8 (2014).","DOI":"10.3389\/fncom.2014.00074"},{"key":"20245_CR59","doi-asserted-by":"crossref","unstructured":"Kheradpisheh, S.\u00a0R., Ghodrati, M., Ganjtabesh, M. & Masquelier, T. Humans and deep networks largely agree on which kinds of variation make object recognition harder. Front. Comput. Neurosci. 10 (2016).","DOI":"10.3389\/fncom.2016.00092"},{"key":"20245_CR60","doi-asserted-by":"publisher","first-page":"e1011713","DOI":"10.1371\/journal.pcbi.1011713","volume":"19","author":"MJ Lee","year":"2023","unstructured":"Lee, M. J. & DiCarlo, J. J. How well do rudimentary plasticity rules predict adult visual object learning?. PLOS Comput. Biol. 19, e1011713 (2023).","journal-title":"PLOS Comput. Biol."},{"key":"20245_CR61","unstructured":"Schrimpf, M. et al. Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like? (2020)."},{"key":"20245_CR62","first-page":"2044","volume":"33","author":"KR Storrs","year":"2021","unstructured":"Storrs, K. R., Kietzmann, T. C., Walther, A., Mehrer, J. & Kriegeskorte, N. Diverse deep neural networks all predict human inferior temporal cortex well, after training and fitting. J. Cognit. Neurosci. 33, 2044\u20132064 (2021).","journal-title":"J. Cognit. Neurosci."},{"key":"20245_CR63","unstructured":"Linsley, D., Feng, P. & Serre, T. Better artificial intelligence does not mean better models of biology (2025). arXiv:2504.16940."},{"key":"20245_CR64","unstructured":"Liao, Q. & Poggio, T. Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex (2020). arXiv:1604.03640."},{"key":"20245_CR65","doi-asserted-by":"crossref","unstructured":"Lonnqvist, B., Clarke, A. D.\u00a0F. & Chakravarthi, R. Crowding in humans is unlike that in convolutional neural networks (2019). arXiv:1903.00258.","DOI":"10.1016\/j.neunet.2020.03.021"},{"key":"20245_CR66","doi-asserted-by":"crossref","unstructured":"Biscione, V. & Bowers, J.\u00a0S. Mixed Evidence for Gestalt Grouping in Deep Neural Networks (2023). arXiv:2203.07302.","DOI":"10.1007\/s42113-023-00169-2"},{"key":"20245_CR67","doi-asserted-by":"crossref","unstructured":"Hosseini, H., Xiao, B., Jaiswal, M. & Poovendran, R. On the Limitation of Convolutional Neural Networks in Recognizing Negative Images (2017). arXiv:1703.06857.","DOI":"10.1109\/ICMLA.2017.0-136"},{"key":"20245_CR68","unstructured":"Fel, T., Felipe, I., Linsley, D. & Serre, T. Harmonizing the object recognition strategies of deep neural networks with humans (2022). arXiv:2211.04533."},{"key":"20245_CR69","doi-asserted-by":"crossref","unstructured":"Nayebi, A. et al. Recurrent Connections in the Primate Ventral Visual Stream Mediate a Tradeoff Between Task Performance and Network Size During Core Object Recognition (2022).","DOI":"10.1101\/2021.02.17.431717"},{"key":"20245_CR70","first-page":"3421","volume":"44","author":"J Wang","year":"2022","unstructured":"Wang, J. & Hu, X. Convolutional neural networks with gated recurrent connections. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3421\u20133435 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20245_CR71","doi-asserted-by":"crossref","unstructured":"Linsley, D., Kim, J., Veerabadran, V. & Serre, T. Learning long-range spatial dependencies with horizontal gated-recurrent units (2019). arXiv:1805.08315.","DOI":"10.32470\/CCN.2018.1116-0"},{"key":"20245_CR72","doi-asserted-by":"crossref","unstructured":"Fukui, H., Hirakawa, T., Yamashita, T. & Fujiyoshi, H. Attention branch network: Learning of attention mechanism for visual explanation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10705\u201310714 (2019).","DOI":"10.1109\/CVPR.2019.01096"},{"key":"20245_CR73","unstructured":"Lotter, W., Kreiman, G. & Cox, D. Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning (2017). arXiv:1605.08104."},{"key":"20245_CR74","doi-asserted-by":"crossref","unstructured":"Lazar, A., Pipa, G. & Triesch, J. SORN: A self-organizing recurrent neural network. Front. Comput. Neurosci. 3 (2009).","DOI":"10.3389\/neuro.10.019.2009"},{"key":"20245_CR75","unstructured":"Konkle, T. & Alvarez, G. A. Cognitive steering in deep neural networks via long-range modulatory feedback connections. In Thirty-Seventh Conference on Neural Information Processing Systems (2023)."},{"key":"20245_CR76","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1167\/jov.21.13.6","volume":"21","author":"MR Ernst","year":"2021","unstructured":"Ernst, M. R., Burwick, T. & Triesch, J. Recurrent processing improves occluded object recognition and gives rise to perceptual hysteresis. J. Vis. 21, 6 (2021).","journal-title":"J. Vis."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20245-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20245-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20245-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:38:22Z","timestamp":1760711902000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20245-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":76,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["20245"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-20245-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"18 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"36344"}}