{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T22:25:14Z","timestamp":1794349514354,"version":"4.9.0"},"reference-count":82,"publisher":"Elsevier BV","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008732","name":"The Uehara Memorial Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008732","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","award":["R01EY032085"],"award-info":[{"award-number":["R01EY032085"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007263","name":"Astellas Foundation for Research on Metabolic Disorders","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007263","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000888","name":"W M Keck Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000888","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["cell.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["iScience"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.isci.2026.117370","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T15:15:28Z","timestamp":1789658128000},"page":"117370","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["Systematic image perturbations reveal persistent gaps between human and machine vision"],"prefix":"10.1016","volume":"29","author":[{"given":"Mugihiko","family":"Kato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1549-1351","authenticated-orcid":false,"given":"Biyu J.","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.isci.2026.117370_bib1","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1146\/annurev-vision-112823-030616","article-title":"The quest for an integrated set of neural mechanisms underlying object recognition in primates","volume":"10","author":"Kar","year":"2024","journal-title":"Annu. Rev. Vision Sci."},{"key":"10.1016\/j.isci.2026.117370_bib2","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"10.1016\/j.isci.2026.117370_bib3","series-title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification","first-page":"1026","author":"He","year":"2015"},{"key":"10.1016\/j.isci.2026.117370_bib4","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"Evaluating Machine Accuracy on ImageNet","author":"Shankar","year":"2020"},{"key":"10.1016\/j.isci.2026.117370_bib5","doi-asserted-by":"crossref","DOI":"10.1038\/srep27755","article-title":"Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence","volume":"6","author":"Cichy","year":"2016","journal-title":"Sci. Rep."},{"key":"10.1016\/j.isci.2026.117370_bib6","doi-asserted-by":"crossref","first-page":"10005","DOI":"10.1523\/JNEUROSCI.5023-14.2015","article-title":"Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream","volume":"35","author":"G\u00fc\u00e7l\u00fc","year":"2015","journal-title":"J. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib7","doi-asserted-by":"crossref","DOI":"10.1038\/ncomms15037","article-title":"Generic decoding of seen and imagined objects using hierarchical visual features","volume":"8","author":"Horikawa","year":"2017","journal-title":"Nat. Commun."},{"key":"10.1016\/j.isci.2026.117370_bib8","doi-asserted-by":"crossref","first-page":"8619","DOI":"10.1073\/pnas.1403112111","article-title":"Performance-optimized hierarchical models predict neural responses in higher visual cortex","volume":"111","author":"Yamins","year":"2014","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"10.1016\/j.isci.2026.117370_bib9","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1038\/nn.4244","article-title":"Using goal-driven deep learning models to understand sensory cortex","volume":"19","author":"Yamins","year":"2016","journal-title":"Nat. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib10","doi-asserted-by":"crossref","first-page":"9383","DOI":"10.1038\/s41467-024-53147-y","article-title":"A large-scale examination of inductive biases shaping high-level visual representation in brains and machines","volume":"15","author":"Conwell","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.isci.2026.117370_bib11","first-page":"23885","article-title":"Partial success in closing the gap between human and machine vision","volume":"34","author":"Geirhos","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.isci.2026.117370_bib12","article-title":"Intriguing Properties of Neural Networks","author":"Szegedy","year":"2013","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib13","article-title":"Generalisation in humans and deep neural networks","volume":"31","author":"Geirhos","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.isci.2026.117370_bib14","series-title":"2017 26th International Conference on Computer Communication and Networks (ICCCN)","first-page":"1","article-title":"A study and comparison of human and deep learning recognition performance under visual distortions","author":"Dodge","year":"2017"},{"key":"10.1016\/j.isci.2026.117370_bib15","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pbio.3001418","article-title":"Noise-trained deep neural networks effectively predict human vision and its neural responses to challenging images","volume":"19","author":"Jang","year":"2021","journal-title":"PLoS Biol."},{"key":"10.1016\/j.isci.2026.117370_bib16","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1167\/jov.21.12.6","article-title":"Convolutional neural networks trained with a developmental sequence of blurry to clear images reveal core differences between face and object processing","volume":"21","author":"Jang","year":"2021","journal-title":"J. Vis."},{"key":"10.1016\/j.isci.2026.117370_bib17","article-title":"Human Alignment of Neural Network Representations","author":"Muttenthaler","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib18","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2021.103013","article-title":"Brain hierarchy score: Which deep neural networks are hierarchically brain-like?","volume":"24","author":"Nonaka","year":"2021","journal-title":"iScience"},{"key":"10.1016\/j.isci.2026.117370_bib19","article-title":"Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream","author":"Gokce","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib20","series-title":"International Conference on Learning Representations","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2018"},{"key":"10.1016\/j.isci.2026.117370_bib21","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1006613","article-title":"Deep convolutional networks do not classify based on global object shape","volume":"14","author":"Baker","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.isci.2026.117370_bib22","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1016\/j.conb.2017.08.019","article-title":"Texture and art with deep neural networks","volume":"46","author":"Gatys","year":"2017","journal-title":"Curr. Opin. Neurobiol."},{"key":"10.1016\/j.isci.2026.117370_bib23","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2115302119","article-title":"Texture-like representation of objects in human visual cortex","volume":"119","author":"Jagadeesh","year":"2022","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"10.1016\/j.isci.2026.117370_bib24","article-title":"Approximating Cnns with Bag-Of-Local-Features Models Works Surprisingly Well on Imagenet","author":"Brendel","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib25","doi-asserted-by":"crossref","DOI":"10.1016\/j.isci.2022.104913","article-title":"Deep learning models fail to capture the configural nature of human shape perception","volume":"25","author":"Baker","year":"2022","journal-title":"iScience"},{"key":"10.1016\/j.isci.2026.117370_bib26","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1038\/s41467-021-22078-3","article-title":"Qualitative similarities and differences in visual object representations between brains and deep networks","volume":"12","author":"Jacob","year":"2021","journal-title":"Nat. Commun."},{"key":"10.1016\/j.isci.2026.117370_bib27","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.visres.2020.04.003","article-title":"Local features and global shape information in object classification by deep convolutional neural networks","volume":"172","author":"Baker","year":"2020","journal-title":"Vision Res."},{"key":"10.1016\/j.isci.2026.117370_bib28","article-title":"Contour Integration Underlies Human-like Vision","author":"Lonnqvist","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib29","article-title":"Intriguing Properties of Generative Classifiers","author":"Jaini","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib30","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1038\/s42256-023-00753-y","article-title":"Better models of human high-level visual cortex emerge from natural language supervision with a large and diverse dataset","volume":"5","author":"Wang","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.isci.2026.117370_bib31","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1038\/s42256-025-01049-z","article-title":"Human-like object concept representations emerge naturally in multimodal large language models","volume":"7","author":"Du","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.isci.2026.117370_bib32","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1038\/s41467-024-45679-0","article-title":"Improved modeling of human vision by incorporating robustness to blur in convolutional neural networks","volume":"15","author":"Jang","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.isci.2026.117370_bib33","article-title":"Cornet: Modeling the neural mechanisms of core object recognition","author":"Kubilius","year":"2018","journal-title":"bioRxiv"},{"key":"10.1016\/j.isci.2026.117370_bib34","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.3389\/fpsyg.2017.01551","article-title":"Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition","volume":"8","author":"Spoerer","year":"2017","journal-title":"Front. Psychol."},{"key":"10.1016\/j.isci.2026.117370_bib35","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/219717.219748","article-title":"WordNet: a lexical database for English","volume":"38","author":"Miller","year":"1995","journal-title":"Commun. ACM"},{"key":"10.1016\/j.isci.2026.117370_bib36","first-page":"13890","article-title":"Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency","volume":"33","author":"Geirhos","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.isci.2026.117370_bib37","article-title":"Brain-like object recognition with high-performing shallow recurrent ANNs","volume":"32","author":"Kubilius","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.isci.2026.117370_bib38","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1038\/s41593-019-0392-5","article-title":"Evidence that recurrent circuits are critical to the ventral stream\u2019s execution of core object recognition behavior","volume":"22","author":"Kar","year":"2019","journal-title":"Nat. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib39","doi-asserted-by":"crossref","first-page":"8835","DOI":"10.1073\/pnas.1719397115","article-title":"Recurrent computations for visual pattern completion","volume":"115","author":"Tang","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"10.1016\/j.isci.2026.117370_bib40","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007001","article-title":"Beyond core object recognition: Recurrent processes account for object recognition under occlusion","volume":"15","author":"Rajaei","year":"2019","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.isci.2026.117370_bib41","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.neuron.2020.09.035","article-title":"Fast Recurrent Processing via Ventrolateral Prefrontal Cortex Is Needed by the Primate Ventral Stream for Robust Core Visual Object Recognition","volume":"109","author":"Kar","year":"2021","journal-title":"Neuron"},{"key":"10.1016\/j.isci.2026.117370_bib42","article-title":"An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib43","article-title":"Clip Itself Is a Strong Fine-Tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with Vit-B and Vit-L on Imagenet","author":"Dong","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib44","article-title":"Brain-score: Which artificial neural network for object recognition is most brain-like?","author":"Schrimpf","year":"2018","journal-title":"bioRxiv"},{"key":"10.1016\/j.isci.2026.117370_bib45","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/j.neuron.2020.07.040","article-title":"Integrative Benchmarking to Advance Neurally Mechanistic Models of Human Intelligence","volume":"108","author":"Schrimpf","year":"2020","journal-title":"Neuron"},{"key":"10.1016\/j.isci.2026.117370_bib46","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/j.neuron.2012.01.010","article-title":"How does the brain solve visual object recognition?","volume":"73","author":"DiCarlo","year":"2012","journal-title":"Neuron"},{"key":"10.1016\/j.isci.2026.117370_bib47","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib48","article-title":"How aligned are different alignment metrics?","author":"Ahlert","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib49","article-title":"The large-scale organization of shape processing in the ventral and dorsal pathways","volume":"6","author":"Freud","year":"2017","journal-title":"eLife"},{"key":"10.1016\/j.isci.2026.117370_bib50","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1073\/pnas.0507062103","article-title":"Top-down facilitation of visual recognition","volume":"103","author":"Bar","year":"2006","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"10.1016\/j.isci.2026.117370_bib51","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.25784","article-title":"Dynamic representation of partially occluded objects in primate prefrontal and visual cortex","volume":"6","author":"Fyall","year":"2017","journal-title":"eLife"},{"key":"10.1016\/j.isci.2026.117370_bib52","first-page":"E3340","article-title":"Brain mechanisms for simple perception and bistable perception","volume":"110","author":"Wang","year":"2013","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"10.1016\/j.isci.2026.117370_bib53","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1523\/JNEUROSCI.2314-15.2016","article-title":"Dissociations and Associations between Shape and Category Representations in the Two Visual Pathways","volume":"36","author":"Bracci","year":"2016","journal-title":"J. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib54","doi-asserted-by":"crossref","first-page":"2930","DOI":"10.1038\/s41467-021-23266-x","article-title":"Cortical and subcortical signatures of conscious object recognition","volume":"12","author":"Levinson","year":"2021","journal-title":"Nat. Commun."},{"key":"10.1016\/j.isci.2026.117370_bib55","article-title":"Temporal asymmetries and interactions between dorsal and ventral visual pathways during object recognition","volume":"4","author":"Ayzenberg","year":"2023","journal-title":"Cereb. Cortex Commun."},{"key":"10.1016\/j.isci.2026.117370_bib56","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1038\/nn2036","article-title":"Two hierarchically organized neural systems for object information in human visual cortex","volume":"11","author":"Konen","year":"2008","journal-title":"Nat. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib57","doi-asserted-by":"crossref","first-page":"1220","DOI":"10.1038\/s42256-025-01072-0","article-title":"High-level visual representations in the human brain are aligned with large language models","volume":"7","author":"Doerig","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.isci.2026.117370_bib58","doi-asserted-by":"crossref","first-page":"270","DOI":"10.3758\/s13414-013-0605-z","article-title":"Detecting meaning in RSVP at 13 ms per picture","volume":"76","author":"Potter","year":"2014","journal-title":"Atten. Percept. Psychophys."},{"key":"10.1016\/j.isci.2026.117370_bib59","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1016\/0010-0285(76)90013-X","article-title":"Basic objects in natural categories","volume":"8","author":"Rosch","year":"1976","journal-title":"Cogn. Psychol."},{"key":"10.1016\/j.isci.2026.117370_bib60","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2011417118","article-title":"An ecologically motivated image dataset for deep learning yields better models of human vision","volume":"118","author":"Mehrer","year":"2021","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"10.1016\/j.isci.2026.117370_bib61","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1038\/s41586-025-09631-6","article-title":"Aligning machine and human visual representations across abstraction levels","volume":"647","author":"Muttenthaler","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.isci.2026.117370_bib62","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2417202122","article-title":"Core dimensions of human material perception","volume":"122","author":"Schmidt","year":"2025","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"10.1016\/j.isci.2026.117370_bib63","doi-asserted-by":"crossref","first-page":"4144","DOI":"10.1523\/JNEUROSCI.1822-22.2023","article-title":"A texture statistics encoding model reveals hierarchical feature selectivity across human visual cortex","volume":"43","author":"Henderson","year":"2023","journal-title":"J. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib64","doi-asserted-by":"crossref","DOI":"10.1016\/j.celrep.2025.115429","article-title":"Neural correlates of minimal recognizable configurations in the human brain","volume":"44","author":"Casile","year":"2025","journal-title":"Cell Rep."},{"key":"10.1016\/j.isci.2026.117370_bib65","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1016\/j.tics.2022.09.019","article-title":"Does the brain's ventral visual pathway compute object shape?","volume":"26","author":"Ayzenberg","year":"2022","journal-title":"Trends Cognit. Sci."},{"key":"10.1016\/j.isci.2026.117370_bib66","article-title":"Do monkeys see the way we do? Qualitative similarities and differences between monkey and human perception","author":"Cherian","year":"2025","journal-title":"bioRxiv"},{"key":"10.1016\/j.isci.2026.117370_bib67","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."},{"key":"10.1016\/j.isci.2026.117370_bib68","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004896","article-title":"Deep Neural Networks as a Computational Model for Human Shape Sensitivity","volume":"12","author":"Kubilius","year":"2016","journal-title":"PLoS Comput. Biol."},{"key":"10.1016\/j.isci.2026.117370_bib69","article-title":"Texture synthesis using convolutional neural networks","volume":"28","author":"Gatys","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.isci.2026.117370_bib70","series-title":"Image Style Transfer Using Convolutional Neural Networks","first-page":"2414","author":"Gatys","year":"2016"},{"key":"10.1016\/j.isci.2026.117370_bib71","article-title":"Learning to Generate Line Drawings that Convey Geometry and Semantics","author":"Chan","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib72","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1523\/JNEUROSCI.1546-22.2022","article-title":"The Spatiotemporal Neural Dynamics of Object Recognition for Natural Images and Line Drawings","volume":"43","author":"Singer","year":"2023","journal-title":"J. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib73","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.36068","article-title":"Content-specific activity in frontoparietal and default-mode networks during prior-guided visual perception","volume":"7","author":"Gonz\u00e1lez-Garc\u00eda","year":"2018","journal-title":"eLife"},{"key":"10.1016\/j.isci.2026.117370_bib74","article-title":"Pytorch: An Imperative Style, High-Performance Deep Learning Library","author":"Paszke","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.isci.2026.117370_bib75","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"11976","article-title":"A Convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.isci.2026.117370_bib76","doi-asserted-by":"crossref","first-page":"25278","DOI":"10.52202\/068431-1833","article-title":"Laion-5B: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.isci.2026.117370_bib77","article-title":"OpenCLIP","author":"Ilharco","year":"2025","journal-title":"Zenodo"},{"key":"10.1016\/j.isci.2026.117370_bib78","article-title":"pytorch-image-models","author":"Wightman","year":"2023","journal-title":"Zenodo"},{"key":"10.1016\/j.isci.2026.117370_bib79","series-title":"Your Diffusion Model Is Secretly a Zero-Shot Classifier","first-page":"2206","author":"Li","year":"2023"},{"key":"10.1016\/j.isci.2026.117370_bib80","doi-asserted-by":"crossref","first-page":"7255","DOI":"10.1523\/JNEUROSCI.0388-18.2018","article-title":"Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks","volume":"38","author":"Rajalingham","year":"2018","journal-title":"J. Neurosci."},{"key":"10.1016\/j.isci.2026.117370_bib81","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1038\/s42256-025-01041-7","article-title":"Dimensions underlying the representational alignment of deep neural networks with humans","volume":"7","author":"Mahner","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.isci.2026.117370_bib82","first-page":"4","article-title":"Representational similarity analysis\u2014connecting the branches of systems neuroscience","volume":"2","author":"Kriegeskorte","year":"2008","journal-title":"Front. Syst. Neurosci."}],"container-title":["iScience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2589004226027483?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2589004226027483?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T22:08:03Z","timestamp":1794348483000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2589004226027483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":82,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["S2589004226027483"],"URL":"https:\/\/doi.org\/10.1016\/j.isci.2026.117370","relation":{},"ISSN":["2589-0042"],"issn-type":[{"value":"2589-0042","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Systematic image perturbations reveal persistent gaps between human and machine vision","name":"articletitle","label":"Article Title"},{"value":"iScience","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.isci.2026.117370","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"117370"}}