{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T09:19:28Z","timestamp":1774689568917,"version":"3.50.1"},"reference-count":110,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T00:00:00Z","timestamp":1718236800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1763981"],"award-info":[{"award-number":["1763981"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2123920"],"award-info":[{"award-number":["2123920"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006324","name":"American Psychological Association","doi-asserted-by":"publisher","award":["APA Dissertation Research Grant"],"award-info":[{"award-number":["APA Dissertation Research Grant"]}],"id":[{"id":"10.13039\/100006324","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Humans are extremely robust in our ability to perceive and recognize objects\u2014we see faces in tea stains and can recognize friends on dark streets. Yet, neurocomputational models of primate object recognition have focused on the initial feed-forward pass of processing through the ventral stream and less on the top-down feedback that likely underlies robust object perception and recognition. Aligned with the generative approach, we propose that the visual system actively facilitates recognition by reconstructing the object hypothesized to be in the image. Top-down attention then uses this reconstruction as a template to bias feedforward processing to align with the most plausible object hypothesis. Building on auto-encoder neural networks, our model makes detailed hypotheses about the appearance and location of the candidate objects in the image by reconstructing a complete object representation from potentially incomplete visual input due to noise and occlusion. The model then leverages the best object reconstruction, measured by reconstruction error, to direct the bottom-up process of selectively routing low-level features, a top-down biasing that captures a core function of attention. We evaluated our model using the MNIST-C (handwritten digits under corruptions) and ImageNet-C (real-world objects under corruptions) datasets. Not only did our model achieve superior performance on these challenging tasks designed to approximate real-world noise and occlusion viewing conditions, but also better accounted for human behavioral reaction times and error patterns than a standard feedforward Convolutional Neural Network. Our model suggests that a complete understanding of object perception and recognition requires integrating top-down and attention feedback, which we propose is an object reconstruction.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012159","type":"journal-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T13:28:36Z","timestamp":1718285316000},"page":"e1012159","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["The attentive reconstruction of objects facilitates robust object recognition"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7842-9208","authenticated-orcid":true,"given":"Seoyoung","family":"Ahn","sequence":"first","affiliation":[]},{"given":"Hossein","family":"Adeli","sequence":"additional","affiliation":[]},{"given":"Gregory J.","family":"Zelinsky","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2024,6,13]]},"reference":[{"issue":"7","key":"pcbi.1012159.ref001","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1093\/cercor\/12.7.756","article-title":"Effects of Illumination Intensity and Direction on Object Coding in Macaque Inferior Temporal Cortex","volume":"12","author":"R Vogels","year":"2002","journal-title":"Cerebral Cortex"},{"issue":"6","key":"pcbi.1012159.ref002","doi-asserted-by":"crossref","first-page":"3102","DOI":"10.1152\/jn.2002.87.6.3102","article-title":"Contrast Sensitivity in Human Visual Areas and Its Relationship to Object Recognition","volume":"87","author":"G Avidan","year":"2002","journal-title":"Journal of Neurophysiology"},{"issue":"12","key":"pcbi.1012159.ref003","doi-asserted-by":"crossref","first-page":"e1003963","DOI":"10.1371\/journal.pcbi.1003963","article-title":"Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition","volume":"10","author":"CF Cadieu","year":"2014","journal-title":"PLOS Computational Biology"},{"key":"pcbi.1012159.ref004","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":"RM Cichy","year":"2016","journal-title":"Scientific Reports"},{"key":"pcbi.1012159.ref005","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1146\/annurev-vision-082114-035447","article-title":"Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing","volume":"1","author":"N Kriegeskorte","year":"2015","journal-title":"Annual Review of Vision Science"},{"issue":"3","key":"pcbi.1012159.ref006","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":"M Schrimpf","year":"2020","journal-title":"Neuron"},{"key":"pcbi.1012159.ref007","first-page":"23885","article-title":"Partial Success in Closing the Gap between Human and Machine Vision","volume":"34","author":"R Geirhos","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pcbi.1012159.ref008","unstructured":"Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, et al. Intriguing Properties of Neural Networks. arXiv:13126199. 2013;."},{"key":"pcbi.1012159.ref009","doi-asserted-by":"crossref","unstructured":"Dodge S, Karam L. A Study and Comparison of Human and Deep Learning Recognition Performance under Visual Distortions. In: International Conference on Computer Communication and Networks (ICCCN); 2017. p. 1\u20137.","DOI":"10.1109\/ICCCN.2017.8038465"},{"issue":"12","key":"pcbi.1012159.ref010","doi-asserted-by":"crossref","first-page":"e1006613","DOI":"10.1371\/journal.pcbi.1006613","article-title":"Deep Convolutional Networks Do Not Classify Based on Global Object Shape","volume":"14","author":"N Baker","year":"2018","journal-title":"PLOS Computational Biology"},{"key":"pcbi.1012159.ref011","unstructured":"Geirhos R, Rubisch P, Michaelis C, Bethge M, Wichmann FA, Brendel W. ImageNet-trained CNNs Are Biased towards Texture; Increasing Shape Bias Improves Accuracy and Robustness. In: International Conference on Learning Representations; 2018."},{"issue":"2","key":"pcbi.1012159.ref012","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1037\/0033-295X.94.2.115","article-title":"Recognition-by-Components: A Theory of Human Image Understanding","volume":"94","author":"I Biederman","year":"1987","journal-title":"Psychological Review"},{"issue":"4","key":"pcbi.1012159.ref013","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1111\/j.1467-9280.1990.tb00209.x","article-title":"When Does Human Object Recognition Use a Viewer-Centered Reference Frame?","volume":"1","author":"MJ Tarr","year":"1990","journal-title":"Psychological Science"},{"issue":"4","key":"pcbi.1012159.ref014","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1162\/jocn.1990.2.4.320","article-title":"Visual Object Representation: Interpreting Neurophysiological Data within a Computational Framework","volume":"2","author":"DC Plaut","year":"1990","journal-title":"Journal of Cognitive Neuroscience"},{"issue":"1-2","key":"pcbi.1012159.ref015","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/0376-6357(94)90062-0","article-title":"Brain Mechanisms for Invariant Visual Recognition and Learning","volume":"33","author":"ET Rolls","year":"1994","journal-title":"Behavioural Processes"},{"key":"pcbi.1012159.ref016","volume-title":"Vision: A Computational Investigation into the Human Representation and Processing of Visual Information","author":"D Marr","year":"1982"},{"issue":"3","key":"pcbi.1012159.ref017","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/0010-0277(89)90036-X","article-title":"Aligning Pictorial Descriptions: An Approach to Object Recognition","volume":"32","author":"S Ullman","year":"1989","journal-title":"Cognition"},{"issue":"1","key":"pcbi.1012159.ref018","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/S0734-189X(87)80014-2","article-title":"A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine","volume":"37","author":"GA Carpenter","year":"1987","journal-title":"Computer vision, graphics, and image processing"},{"issue":"1","key":"pcbi.1012159.ref019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/cercor\/5.1.1","article-title":"Sequence Seeking and Counter Streams: A Computational Model for Bidirectional Information Flow in the Visual Cortex","volume":"5","author":"S Ullman","year":"1995","journal-title":"Cerebral cortex"},{"issue":"7","key":"pcbi.1012159.ref020","doi-asserted-by":"crossref","first-page":"1434","DOI":"10.1364\/JOSAA.20.001434","article-title":"Hierarchical Bayesian Inference in the Visual Cortex","volume":"20","author":"TS Lee","year":"2003","journal-title":"Journal of the Optical Society of America A"},{"issue":"2","key":"pcbi.1012159.ref021","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1073\/pnas.0507062103","article-title":"Top-down Facilitation of Visual Recognition","volume":"103","author":"M Bar","year":"2006","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"5","key":"pcbi.1012159.ref022","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/nrn3476","article-title":"Top-down Influences on Visual Processing","volume":"14","author":"CD Gilbert","year":"2013","journal-title":"Nature Reviews Neuroscience"},{"issue":"1","key":"pcbi.1012159.ref023","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1080\/00335558008248231","article-title":"Orienting of Attention","volume":"32","author":"MI Posner","year":"1980","journal-title":"Quarterly Journal of Experimental Psychology"},{"issue":"2","key":"pcbi.1012159.ref024","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1111\/1467-9280.00422","article-title":"Can the Spotlight of Attention Be Shaped like a Doughnut? Evidence from Steady-State Visual Evoked Potentials","volume":"13","author":"MM M\u00fcller","year":"2002","journal-title":"Psychological Science"},{"issue":"2","key":"pcbi.1012159.ref025","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1080\/02724988843000104","article-title":"Features and Objects: The Fourteenth Bartlett Memorial Lecture","volume":"40","author":"A Treisman","year":"1988","journal-title":"The Quarterly Journal of Experimental Psychology Section A"},{"issue":"9","key":"pcbi.1012159.ref026","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.cub.2004.04.028","article-title":"Feature-Based Attention Increases the Selectivity of Population Responses in Primate Visual Cortex","volume":"14","author":"JC Martinez-Trujillo","year":"2004","journal-title":"Current Biology"},{"issue":"3","key":"pcbi.1012159.ref027","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":"JJ DiCarlo","year":"2012","journal-title":"Neuron"},{"key":"pcbi.1012159.ref028","article-title":"The Architecture of Object-Based Attention","author":"P Cavanagh","year":"2023","journal-title":"Psychonomic Bulletin & Review"},{"issue":"5","key":"pcbi.1012159.ref029","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1162\/neco.1995.7.5.889","article-title":"The Helmholtz Machine","volume":"7","author":"P Dayan","year":"1995","journal-title":"Neural Computation"},{"issue":"7","key":"pcbi.1012159.ref030","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.tics.2006.05.002","article-title":"Vision as Bayesian Inference: Analysis by Synthesis?","volume":"10","author":"A Yuille","year":"2006","journal-title":"Trends in Cognitive Sciences"},{"issue":"9","key":"pcbi.1012159.ref031","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1016\/j.tics.2018.06.002","article-title":"How Do Expectations Shape Perception?","volume":"22","author":"FP de Lange","year":"2018","journal-title":"Trends in Cognitive Sciences"},{"issue":"3","key":"pcbi.1012159.ref032","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1017\/S0140525X12000477","article-title":"Whatever next? Predictive Brains, Situated Agents, and the Future of Cognitive Science","volume":"36","author":"A Clark","year":"2013","journal-title":"Behavioral and Brain Sciences"},{"issue":"13","key":"pcbi.1012159.ref033","doi-asserted-by":"crossref","first-page":"1484","DOI":"10.1016\/j.visres.2011.04.012","article-title":"Visual Attention: The Past 25 Years","volume":"51","author":"M Carrasco","year":"2011","journal-title":"Vision Research"},{"issue":"8","key":"pcbi.1012159.ref034","doi-asserted-by":"crossref","first-page":"2434","DOI":"10.3758\/s13414-011-0201-z","article-title":"Space-, Object-, and Feature-Based Attention Interact to Organize Visual Scenes","volume":"73","author":"DJ Kravitz","year":"2011","journal-title":"Attention, Perception, & Psychophysics"},{"issue":"5","key":"pcbi.1012159.ref035","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1167\/jov.23.5.16","article-title":"A Brain-Inspired Object-Based Attention Network for Multiobject Recognition and Visual Reasoning","volume":"23","author":"H Adeli","year":"2023","journal-title":"Journal of Vision"},{"key":"pcbi.1012159.ref036","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.cobeha.2019.07.004","article-title":"Learning to See Stuff","volume":"30","author":"RW Fleming","year":"2019","journal-title":"Current Opinion in Behavioral Sciences"},{"issue":"45","key":"pcbi.1012159.ref037","doi-asserted-by":"crossref","first-page":"e2202024119","DOI":"10.1073\/pnas.2202024119","article-title":"Linking Global Top-down Views to First-Person Views in the Brain","volume":"119","author":"J Xing","year":"2022","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"3","key":"pcbi.1012159.ref038","doi-asserted-by":"crossref","first-page":"e1008775","DOI":"10.1371\/journal.pcbi.1008775","article-title":"Reconstructing Feedback Representations in the Ventral Visual Pathway with a Generative Adversarial Autoencoder","volume":"17","author":"H Al-Tahan","year":"2021","journal-title":"PLOS Computational Biology"},{"issue":"5","key":"pcbi.1012159.ref039","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1038\/s41562-021-01264-9","article-title":"A Model of Working Memory for Latent Representations","volume":"6","author":"S Hedayati","year":"2022","journal-title":"Nature Human Behaviour"},{"issue":"10","key":"pcbi.1012159.ref040","doi-asserted-by":"crossref","first-page":"eaax5979","DOI":"10.1126\/sciadv.aax5979","article-title":"Efficient Inverse Graphics in Biological Face Processing","volume":"6","author":"I Yildirim","year":"2020","journal-title":"Science Advances"},{"key":"pcbi.1012159.ref041","volume-title":"Advances in Neural Information Processing System Workshops","author":"V Boutin","year":"2020"},{"key":"pcbi.1012159.ref042","unstructured":"Csikor F, Mesz\u00e9na B, Szab\u00f3 B, Orb\u00e1n G. Top-down Inference in an Early Visual Cortex Inspired Hierarchical Variational Autoencoder. arXiv preprint arXiv: 220600436. 2022;."},{"key":"pcbi.1012159.ref043","unstructured":"Mu N, Gilmer J. MNIST-C: A Robustness Benchmark for Computer Vision. arXiv:190602337. 2019;."},{"key":"pcbi.1012159.ref044","unstructured":"Hendrycks D, Dietterich TG. Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. International Conference On Learning Representations. 2019;."},{"key":"pcbi.1012159.ref045","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"pcbi.1012159.ref046","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/nrn2787","article-title":"The Free-Energy Principle: A Unified Brain Theory?","volume":"11","author":"K Friston","year":"2010","journal-title":"Nature Reviews Neuroscience"},{"key":"pcbi.1012159.ref047","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.neunet.2016.11.003","article-title":"Towards Solving the Hard Problem of Consciousness: The Varieties of Brain Resonances and the Conscious Experiences That They Support","volume":"87","author":"S Grossberg","year":"2017","journal-title":"Neural Networks"},{"issue":"1","key":"pcbi.1012159.ref048","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cogpsych.2008.05.001","article-title":"View-Invariant Object Category Learning, Recognition, and Search: How Spatial and Object Attention Are Coordinated Using Surface-Based Attentional Shrouds","volume":"58","author":"A Fazl","year":"2009","journal-title":"Cognitive Psychology"},{"issue":"3","key":"pcbi.1012159.ref049","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1037\/0033-295X.99.3.480","article-title":"Dynamic Binding in a Neural Network for Shape Recognition","volume":"99","author":"JE Hummel","year":"1992","journal-title":"Psychological Review"},{"issue":"2","key":"pcbi.1012159.ref050","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1016\/j.neuron.2019.02.001","article-title":"Reversible Inactivation of Different Millimeter-Scale Regions of Primate IT Results in Different Patterns of Core Object Recognition Deficits","volume":"102","author":"R Rajalingham","year":"2019","journal-title":"Neuron"},{"key":"pcbi.1012159.ref051","first-page":"3856","volume-title":"Advances in Neural Information Processing Systems","author":"S Sabour","year":"2017"},{"issue":"7","key":"pcbi.1012159.ref052","doi-asserted-by":"crossref","first-page":"e1008017","DOI":"10.1371\/journal.pcbi.1008017","article-title":"Capsule Networks as Recurrent Models of Grouping and Segmentation","volume":"16","author":"A Doerig","year":"2020","journal-title":"PLOS Computational Biology"},{"key":"pcbi.1012159.ref053","unstructured":"Greff K, van Steenkiste S, Schmidhuber J. On the Binding Problem in Artificial Neural Networks. arXiv:201205208. 2020;."},{"key":"pcbi.1012159.ref054","first-page":"11525","article-title":"Object-Centric Learning with Slot Attention","volume":"33","author":"F Locatello","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"pcbi.1012159.ref055","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/0010-0285(92)90007-O","article-title":"The Reviewing of Object Files: Object-specific Integration of Information","volume":"24","author":"D Kahneman","year":"1992","journal-title":"Cognitive Psychology"},{"issue":"6","key":"pcbi.1012159.ref056","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1177\/0956797616640237","article-title":"Searching for Category-Consistent Features: A Computational Approach to Understanding Visual Category Representation","volume":"27","author":"CP Yu","year":"2016","journal-title":"Psychological Science"},{"issue":"9","key":"pcbi.1012159.ref057","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1038\/s41562-021-01194-6","article-title":"Capturing the Objects of Vision with Neural Networks","volume":"5","author":"B Peters","year":"2021","journal-title":"Nature Human Behaviour"},{"issue":"5786","key":"pcbi.1012159.ref058","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the Dimensionality of Data with Neural Networks","volume":"313","author":"GE Hinton","year":"2006","journal-title":"Science"},{"key":"pcbi.1012159.ref059","author":"V Dumoulin","year":"2018","journal-title":"A Guide to Convolution Arithmetic for Deep Learning"},{"issue":"6809","key":"pcbi.1012159.ref060","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1038\/35041567","article-title":"Tracking an Object through Feature Space","volume":"408","author":"E Blaser","year":"2000","journal-title":"Nature"},{"issue":"2","key":"pcbi.1012159.ref061","doi-asserted-by":"crossref","first-page":"301","DOI":"10.3758\/BF03196376","article-title":"The Spread of Attention to Hidden Portions of Occluded Surfaces","volume":"12","author":"CM Moore","year":"2005","journal-title":"Psychonomic Bulletin & Review"},{"issue":"1","key":"pcbi.1012159.ref062","first-page":"139","article-title":"Is There a Shape to the Attention Spotlight? Computing Saliency over Proto-Objects Predicts Fixations during Scene Viewing","volume":"45","author":"Y Chen","year":"2019","journal-title":"Journal of Experimental Psychology: Human Perception and Performance"},{"issue":"2","key":"pcbi.1012159.ref063","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1068\/p240127","article-title":"Mechanisms of Stereoscopic Processing: Stereoattention and Surface Perception in Depth Reconstruction","volume":"24","author":"CW Tyler","year":"1995","journal-title":"Perception"},{"issue":"2","key":"pcbi.1012159.ref064","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.conb.2004.03.012","article-title":"Parietal Cortex and Attention","volume":"14","author":"M Behrmann","year":"2004","journal-title":"Current Opinion in Neurobiology"},{"issue":"11","key":"pcbi.1012159.ref065","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1016\/j.tins.2018.07.012","article-title":"The Posterior Parietal Cortex in Adaptive Visual Processing","volume":"41","author":"Y Xu","year":"2018","journal-title":"Trends in Neurosciences"},{"key":"pcbi.1012159.ref066","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R. Masked Autoencoders Are Scalable Vision Learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2022. p. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"6","key":"pcbi.1012159.ref067","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1016\/j.visres.2003.09.037","article-title":"A Neurodynamical Cortical Model of Visual Attention and Invariant Object Recognition","volume":"44","author":"G Deco","year":"2004","journal-title":"Vision Research"},{"key":"pcbi.1012159.ref068","doi-asserted-by":"crossref","first-page":"e14320","DOI":"10.7554\/eLife.14320","article-title":"Serial Grouping of 2D-image Regions with Object-Based Attention in Humans","volume":"5","author":"D Jeurissen","year":"2016","journal-title":"Elife"},{"issue":"1","key":"pcbi.1012159.ref069","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","article-title":"Neural Mechanisms of Selective Visual Attention","volume":"18","author":"R Desimone","year":"1995","journal-title":"Annual Review of Neuroscience"},{"issue":"10","key":"pcbi.1012159.ref070","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.1016\/j.visres.2008.07.012","article-title":"Top-down and Bottom-up Mechanisms in Biasing Competition in the Human Brain","volume":"49","author":"DM Beck","year":"2009","journal-title":"Vision Research"},{"issue":"6","key":"pcbi.1012159.ref071","doi-asserted-by":"crossref","first-page":"1446","DOI":"10.1016\/j.neuropsychologia.2010.12.006","article-title":"A Neural Theory of Visual Attention and Short-Term Memory (NTVA)","volume":"49","author":"C Bundesen","year":"2011","journal-title":"Neuropsychologia"},{"key":"pcbi.1012159.ref072","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A Large-Scale Hierarchical Image Database. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2009. p. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"pcbi.1012159.ref073","volume-title":"Advances in Neural Information Processing System","author":"R Geirhos","year":"2018"},{"key":"pcbi.1012159.ref074","first-page":"17864","article-title":"Per-Pixel Classification Is Not All You Need for Semantic Segmentation","volume":"34","author":"B Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pcbi.1012159.ref075","author":"JJ DiCarlo","year":"2021","journal-title":"How Does the Brain Combine Generative Models and Direct Discriminative Computations in High-Level Vision?"},{"key":"pcbi.1012159.ref076","doi-asserted-by":"crossref","first-page":"18","DOI":"10.3389\/frai.2019.00018","article-title":"The Generative Adversarial Brain","volume":"2","author":"SJ Gershman","year":"2019","journal-title":"Frontiers in Artificial Intelligence"},{"issue":"12","key":"pcbi.1012159.ref077","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1016\/j.cub.2020.04.014","article-title":"Generative Feedback Explains Distinct Brain Activity Codes for Seen and Mental Images","volume":"30","author":"JL Breedlove","year":"2020","journal-title":"Current Biology"},{"key":"pcbi.1012159.ref078","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/978-3-0348-9110-3_6","volume-title":"First European Congress of Mathematics: Paris, July 6-10, 1992 Volume I Invited Lectures (Part 1)","author":"D Mumford","year":"1994"},{"issue":"3","key":"pcbi.1012159.ref079","first-page":"775","article-title":"Prototypes in Category Learning: The Effects of Category Size, Category Structure, and Stimulus Complexity","volume":"27","author":"JP Minda","year":"2001","journal-title":"Journal of Experimental Psychology: Learning, Memory, and Cognition"},{"issue":"4","key":"pcbi.1012159.ref080","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1162\/089892903321662976","article-title":"A Cortical Mechanism for Triggering Top-down Facilitation in Visual Object Recognition","volume":"15","author":"M Bar","year":"2003","journal-title":"Journal of Cognitive Neuroscience"},{"key":"pcbi.1012159.ref081","article-title":"Top-down Generation of Low-Precision Representations Improves the Perception and Imagination of Fine-Scale Visual Information","author":"Z Bi","year":"2021","journal-title":"bioRxiv"},{"issue":"6","key":"pcbi.1012159.ref082","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.tins.2006.04.001","article-title":"Feature-Based Attention in Visual Cortex","volume":"29","author":"JH Maunsell","year":"2006","journal-title":"Trends in Neurosciences"},{"key":"pcbi.1012159.ref083","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"J Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pcbi.1012159.ref084","unstructured":"Singh G, Deng F, Ahn S. Illiterate DALL-E Learns to Compose. In: International Conference on Learning Representations; 2022."},{"key":"pcbi.1012159.ref085","article-title":"Shared Neural Mechanisms of Visual Perception and Imagery","author":"N Dijkstra","year":"2019","journal-title":"Trends in Cognitive Sciences"},{"issue":"2","key":"pcbi.1012159.ref086","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1037\/0096-3445.123.2.161","article-title":"Shifting Visual Attention between Objects and Locations: Evidence from Normal and Parietal Lesion Subjects","volume":"123","author":"R Egly","year":"1994","journal-title":"Journal of Experimental Psychology: General"},{"issue":"3","key":"pcbi.1012159.ref087","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1023\/A:1011565623996","article-title":"Toward a Biased Competition Account of Object-Based Segregation and Attention","volume":"1","author":"SP Vecera","year":"2000","journal-title":"Brain and Mind"},{"issue":"1-2","key":"pcbi.1012159.ref088","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0010-0277(00)00152-9","article-title":"Objects and Attention: The State of the Art","volume":"80","author":"BJ Scholl","year":"2001","journal-title":"Cognition"},{"issue":"4","key":"pcbi.1012159.ref089","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1037\/0033-295X.103.4.603","article-title":"The CODE Theory of Visual Attention: An Integration of Space-Based and Object-Based Attention","volume":"103","author":"GD Logan","year":"1996","journal-title":"Psychological Review"},{"issue":"8","key":"pcbi.1012159.ref090","doi-asserted-by":"crossref","first-page":"2542","DOI":"10.3758\/s13414-011-0200-0","article-title":"Incremental Grouping of Image Elements in Vision","volume":"73","author":"PR Roelfsema","year":"2011","journal-title":"Attention, Perception, & Psychophysics"},{"issue":"6","key":"pcbi.1012159.ref091","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1037\/a0029333","article-title":"A Century of Gestalt Psychology in Visual Perception: I. Perceptual Grouping and Figure\u2013Ground Organization","volume":"138","author":"J Wagemans","year":"2012","journal-title":"Psychological Bulletin"},{"key":"pcbi.1012159.ref092","volume-title":"The Oxford Handbook of Attention","author":"M Scolari","year":"2014"},{"issue":"30","key":"pcbi.1012159.ref093","doi-asserted-by":"crossref","first-page":"11387","DOI":"10.1073\/pnas.0601813103","article-title":"Cortical Systems Mediating Visual Attention to Both Objects and Spatial Locations","volume":"103","author":"S Shomstein","year":"2006","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"4","key":"pcbi.1012159.ref094","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.1093\/cercor\/bht303","article-title":"Neural Mechanisms of Object-Based Attention","volume":"25","author":"EH Cohen","year":"2015","journal-title":"Cerebral Cortex"},{"issue":"6753","key":"pcbi.1012159.ref095","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1038\/44134","article-title":"fMRI Evidence for Objects as the Units of Attentional Selection","volume":"401","author":"KM O\u2019Craven","year":"1999","journal-title":"Nature"},{"issue":"1","key":"pcbi.1012159.ref096","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/0010-0277(89)90014-0","article-title":"The Role of Location Indexes in Spatial Perception: A Sketch of the FINST Spatial-Index Model","volume":"32","author":"Z Pylyshyn","year":"1989","journal-title":"Cognition"},{"issue":"1","key":"pcbi.1012159.ref097","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1038\/s41467-023-37322-1","article-title":"Subjective Signal Strength Distinguishes Reality from Imagination","volume":"14","author":"N Dijkstra","year":"2023","journal-title":"Nature Communications"},{"key":"pcbi.1012159.ref098","unstructured":"Dittadi A, Papa SS, Vita MD, Sch\u00f6lkopf B, Winther O, Locatello F. Generalization and Robustness Implications in Object-Centric Learning. In: International Conference on Machine Learning. vol. 162 of Proceedings of Machine Learning Research. PMLR; 2022. p. 5221\u20135285."},{"key":"pcbi.1012159.ref099","doi-asserted-by":"crossref","unstructured":"Shi B, Darrell T, Wang X. Top-down Visual Attention from Analysis by Synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2023. p. 2102\u20132112.","DOI":"10.1109\/CVPR52729.2023.00209"},{"issue":"1","key":"pcbi.1012159.ref100","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"N Srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"issue":"6","key":"pcbi.1012159.ref101","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The MNIST Database of Handwritten Digit Images for Machine Learning Research","volume":"29","author":"L Deng","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"pcbi.1012159.ref102","unstructured":"Kingma DP, Ba J. Adam: A Method for Stochastic Optimization. arXiv:14126980. 2014;."},{"issue":"10","key":"pcbi.1012159.ref103","doi-asserted-by":"crossref","first-page":"e1008215","DOI":"10.1371\/journal.pcbi.1008215","article-title":"Recurrent Neural Networks Can Explain Flexible Trading of Speed and Accuracy in Biological Vision","volume":"16","author":"CJ Spoerer","year":"2020","journal-title":"PLOS Computational Biology"},{"issue":"13","key":"pcbi.1012159.ref104","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1167\/jov.21.13.13","article-title":"Use of Superordinate Labels Yields More Robust and Human-like Visual Representations in Convolutional Neural Networks","volume":"21","author":"S Ahn","year":"2021","journal-title":"Journal of Vision"},{"issue":"2","key":"pcbi.1012159.ref105","doi-asserted-by":"crossref","first-page":"175","DOI":"10.3758\/BF03193146","article-title":"G*Power 3: A Flexible Statistical Power Analysis Program for the Social, Behavioral, and Biomedical Sciences","volume":"39","author":"F Faul","year":"2007","journal-title":"Behavior Research Methods"},{"key":"pcbi.1012159.ref106","unstructured":"Schott L, Rauber J, Bethge M, Brendel W. Towards the First Adversarially Robust Neural Network Model on MNIST. In: International Conference on Learning Representations; 2018."},{"key":"pcbi.1012159.ref107","unstructured":"Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A. Towards Deep Learning Models Resistant to Adversarial Attacks. In: International Conference on Learning Representations; 2018."},{"key":"pcbi.1012159.ref108","doi-asserted-by":"crossref","unstructured":"Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C, et al. ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. In: Proceedings of the European Conference on Computer Vision Workshops; 2018.","DOI":"10.1007\/978-3-030-11021-5_5"},{"issue":"3","key":"pcbi.1012159.ref109","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1037\/h0047313","article-title":"A Mechanical Model for Human Attention and Immediate Memory","volume":"64","author":"DE Broadbent","year":"1957","journal-title":"Psychological Review"},{"key":"pcbi.1012159.ref110","volume-title":"The Psychology of Attention","author":"H Pashler","year":"1998"}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T13:30:12Z","timestamp":1718285412000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012159"}},"subtitle":[],"editor":[{"given":"Christoph","family":"Strauch","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,6,13]]},"references-count":110,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,6,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012159","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.07.17.549340","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,13]]}}}