脑启发的视觉目标识别模型研究与展望

doi:10.3778/j.issn.1002-8331.2110-0253

摘要/Abstract

摘要： 视觉目标识别是计算机视觉领域中最基本、最具有挑战性的研究课题之一。由于灵长类出色的视觉目标识别能力，对其神经功能机理的研究可能为类脑视觉带来革命性的突破。旨在系统地回顾最近在计算神经科学和计算机视觉交叉领域的工作，研究当前基于脑启发的目标识别模型及其依据的视觉神经机制。从认知功能和皮层动力学方面总结了灵长类视觉目标识别机制的基本特征和主要贡献；根据技术架构和开发方式总结了基于大脑启发的目标识别模型及其实现类脑目标识别的优缺点。进一步对人工神经网络与视觉神经网络进行相似性分析，研究了当前流行的CNN视觉基准模型在生物学上的可信性。总结了当前视觉目标识别常用的实验设计条件和数据分析方法，可以作为一个研究人员进行视觉目标识别研究时权衡时机和条件的使用指南。

关键词: 类脑视觉, 目标识别模型, 神经机制, 深度神经网络

Abstract: Visual object recognition is one of the most fundamental and challenging research topics in the field of computer vision. The research on the neural mechanism of the primates’ recognition function may bring revolutionary breakthroughs in brain-inspired vision. This review aims to systematically review the recent works on the intersection of computational neuroscience and computer vision. It attempts to investigate the current brain-inspired object recognition models and their underlying visual neural mechanism. According to the technical architecture and exploitation methods, the paper describes the brain-inspired object recognition models and their advantages and disadvantages in realizing brain-inspired object recognition. It focuses on analyzing the similarity between the artificial and biological neural network, and studying the biological credibility of the current popular DNN-based visual benchmark models. The analysis provides a guide for researchers to measure the occasion and condition when conducting visual object recognition research.

Key words: brain-inspired vision, model for object recognition, neural mechanisms, deep neural network

杨曦, 闫杰, 王文, 李少毅, 林健. 脑启发的视觉目标识别模型研究与展望[J]. 计算机工程与应用, 2022, 58(7): 1-20.

YANG Xi, YAN Jie, WANG Wen, LI Shaoyi, LIN Jian. Research and Prospect of Brain-Inspired Model for Visual Object Recognition[J]. Computer Engineering and Applications, 2022, 58(7): 1-20.

参考文献

[1] WANG G，OBAMA S，YAMASHITA W，et al.Prior experience of rotation is not required for recognizing objects seen from different angles[J].Nature Neuroscience，2005，8（12）：1568-1575.
[2] HUBEL D H.Receptive-fields，binocular interaction and functional architecture in the cats visual-cortex[J].Current Contents/Life Sciences，1985，19：23.
[3] HUBEL D H，WIESEL T N.Receptive fields of single neurones in the cats striate cortex[J].Journal of Physiology-London，1959，148（3）：574-591.
[4] RIESENHUBER M，POGGIO T.Hierarchical models of object recognition in cortex[J].Nature Neuroscience，1999，2（11）：1019-1025.
[5] TARR M J.News on views：Pandemonium revisited[J].Nature Neuroscience，1999，2（11）：932-935.
[6] SMIRNOV E A，TIMOSHENKO D M，ANDRIANOV S N.Comparison of regularization methods for ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 2nd AASRI Conference on Computational Intelligence and Bioinformatics，2014：89-94.
[7] CAO C S，LIU X M，YANG Y，et al.Look and think twice：Capturing top-down visual attention with feedback convolutional neural networks[C]//Proceedings of 2015 IEEE International Conference on Computer Vision，2015：2956-2964.
[8] SPAMPINATO C，PALAZZO S，KAVASIDIS I，et al.Deep learning human mind for automated visual classification[C]//Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition，2017：4503-4511.
[9] MEL B W.SEEMORE：Combining color，shape，and texture histogramming in a neurally inspired approach to visual object recognition[J].Neural Computation，1997，9（4）：777-804.
[10] RYBAK I A，GUSAKOVA V I，GOLOVAN A V，et al.A model of attention-guided visual perception and recognition[J].Vision Research，1998，38（15/16）：2387-2400.
[11] SERRE T，WOLF L，BILESCHI S，et al.Robust object recognition with cortex-like mechanisms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2007，29（3）：411-426.
[12] PARK M S，ZHANG C J，DEBOLE M，et al.Accelerators for biologically-inspired attention and recognition[C]//Proceedings of 2013 50th ACM/EDAC/IEEE Design Automation Conference，2013：1-6.
[13] LU Y F，QIAO H，LI Y，et al.Image recommendation based on a novel biologically inspired hierarchical model[J].Multimedia Tools and Applications，2018，77（4）：4323-4337.
[14] KARIMIMEHR S，YAZDCHI M R.How computational neuroscience could help improving face recognition systems?[C]//Proceedings of 2014 4th International Conference on Computer and Knowledge Engineering，2014：410-413.
[15] WERSING H，KORNER E.Learning optimized features for hierarchical models of invariant object recognition[J].Neural Computation，2003，15（7）：1559-1588.
[16] LECUN Y，HUANG F J，BOTTOU L.Learning methods for generic object recognition with invariance to pose and lighting[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2004：97-104.
[17] BAIR W.Visual receptive field organization[J].Current Opinion in Neurobiology，2005，15（4）：459-464.
[18] ZHAO X P，WANG L，ZHAN Y H.A perceptual object based attention mechanism for scene analysis[J].Journal of Image and Graphics，2006，11：281-288.
[19] ROUSSELET G A，THORPE S J，FABRE-THORPE M.How parallel is visual processing in the ventral pathway?[J].Trends in Cognitive Sciences，2004，8（8）：363-370.
[20] AZZOPARDI G，PETKOV N.COSFIRE：A brain-inspired approach to visual pattern recognition[J].Brain-Inspired Computing，2014，8603：76-87.
[21] AZZOPARDI G，PETKOV N.Trainable COSFIRE filters for key point detection and pattern recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2013，35（2）：490-503.
[22] AZZOPARDI G，PETKOV N.Automatic detection of vascular bifurcations in segmented retinal images using trainable COSFIRE filters[J].Pattern Recognition Letters，2013，34（8）：922-933.
[23] DECO G，ROLLS E T.A Neurodynamical cortical model of visual attention and invariant object recognition[J].Vision Research，2004，44（6）：621-642.
[24] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communications of the ACM，2017，60（6）：84-90.
[25] MILLER E K，COHEN J D.An integrative theory of prefrontal cortex function[J].Annual Review of Neuroscience，2001，24：167-202.
[26] FUKUSHIMA K.Neocognitron—A self-organizing neural network model for a mechanism of pattern-recognition unaffected by shift in position[J].Biological Cybernetics，1980，36（4）：193-202.
[27] PERRETT D I，ORAM M W.Neurophysiology of shape processing[J].Image and Vision Computing，1993，11（6）：317-333.
[28] WALLIS G，ROLLS E T.Invariant face and object recognition in the visual system[J].Progress in Neurobiology，1997，51（2）：167-194.
[29] SERRE T，KREIMAN G，KOUH M，et al.A quantitative theory of immediate visual recognition[J].Computational Neuroscience：Theoretical Insights into Brain Function，2007，165：33-56.
[30] LE Q V.Building high-level features using large scale unsupervised learning[C]//Proceedings of the 2013 IEEE International Conference on Acoustics，Speech and Signal Processing，2013：8595-8598.
[31] ZEILER M D，FERGUS R.Visualizing and understanding convolutional networks[C]//Proceedings of the International Conference on Computer Vision，2014：818-833.
[32] ZWEIG S，WOLF L.InterpoNet，A brain inspired neural network for optical flow dense interpolation[C]//Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition，2017：6363-6372.
[33] KIM E，HANNAN D，KENYON G.Deep sparse coding for invariant multimodal halle berry neurons[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition，2018：1111-1120.
[34] ADELI H，ZELINSKY G.Deep-BCN：Deep networks meet biased competition to create a brain-inspired model of attention control[C]//Proceedings 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops，2018：2013-2023.
[35] YU C P，LIU H D，SAMARAS D，et al.Modelling attention control using a convolutional neural network designed after the ventral visual pathway[J].Visual Cognition，2019，27：416-434.
[36] WEN H，HAN K，SHI J，et al.Deep predictive coding network for object recognition[J].arXiv：1802.04762，2018.
[37] MONTOBBIO N，BONNASSE-GAHOT L，CITTI G，et al.KerCNNs：Biologically inspired lateral connections for classification of corrupted images[J].arXiv：1910.08336，2019.
[38] DAPELLO J，MARQUES T，SCHRIMPF M，et al.Simulating a primary visual cortex at the front of CNNs improves robustness to image perturbations[J/OL].（2020-06-16）[2021-10-19].https：//doi.org/10.1101/2020.06.16.154542.
[39] PARK Y J，BAEK S，PAIK S B.A brain-inspired network architecture for cost-efficient object recognition in shallow hierarchical neural networks[J].Neural Networks，2021，134：76-85.
[40] PIECH V，LI W，REEKE G N，et al.Network model of top-down influences on local gain and contextual interactions in visual cortex[J].Proceedings of the National Academy of Sciences of the United States of America，2013，110：4108-4117.
[41] KARIMI-ROUZBAHANI H，BAGHERI N，EBRAHIMPOUR R.Invariant object recognition is a personalized selection of invariant features in humans，not simply explained by hierarchical feed-forward vision models[J].Scientific Reports，2017，7：14402.
[42] NASR K，VISWANATHAN P，NIEDER A.Number detectors spontaneously emerge in a deep neural network designed for visual object recognition[J].Science Advances，2019，5（5）：7903.
[43] KIM G，JANG J，BAEK S，et al.Visual number sense in untrained deep neural networks[J].Science Advances，2021，7（1）：6127.
[44] ALBRIGHT T D，STONER G R.Contextual influences on visual processing[J].Annual Review of Neuroscience，2002，25：339-379.
[45] LIANG M，HU X L.Recurrent convolutional neural network for object recognition[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition，2015：3367-3375.
[46] CARLSON T A，HOGENDOORN H，KANAI R，et al.High temporal resolution decoding of object position and category[J].Journal of Vision，2011，11（10）：9.
[47] WANG C M，XIONG S，HU X P，et al.Combining features from ERP components in single-trial EEG for discriminating four-category visual objects[J].Journal of Neural Engineering，2012，9（5）：056013.
[48] YAMINS D L K，HONG H，CADIEU C F，et al.Performance-optimized hierarchical models predict neural responses in higher visual cortex[J].Proceedings of the National Academy of Sciences of the United States of America，2014，111：8619-8624.
[49] EICKENBERG M，GRAMFORT A，VAROQUAUX G，et al.Seeing it all：Convolutional network layers map the function of the human visual system[J].Neuroimage，2017，152：184-194.
[50] WEN H G，SHI J X，CHEN W，et al.Transferring and generalizing deep-learning-based neural encoding models across subjects[J].Neuroimage，2018，176：152-163.
[51] WEN H G，SHI J X，CHEN W，et al.Deep residual network predicts cortical representation and organization of visual features for rapid categorization[J].Scientific Reports，2018，8：3752.
[52] SEELIGER K，GUCLU U，AMBROGIONI L，et al.Generative adversarial networks for reconstructing natural images from brain activity[J].Neuroimage，2018，181：775-785.
[53] FEDERER C，XU H Y，FYSHE A，et al.Improved object recognition using neural networks trained to mimic the brain’s statistical properties[J].Neural Networks，2020，131：103-114.
[54] YILDIRIM I，BELLEDONNE M，FREIWALD W，et al.Efficient inverse graphics in biological face processing[J].Science Advances，2020，6（10）：5979.
[55] ZHUANG C X，YAN S M，NAYEBI A，et al.Unsupervised neural network models of the ventral visual stream[J].Proceedings of the National Academy of Sciences of the United States of America，2021，118：155556.
[56] GOODFELLOW I，POUGET-ABADIE J，MIRZA M，et al.Generative adversarial networks[J].Communications of the ACM，2020，63（11）：139-144.
[57] LIU J X，ZHAO G P.A bio-inspired SOSNN model for object recognition[C]//Proceedings of the 2018 International Joint Conference on Neural Networks，2018：861-868.
[58] HEIDARI-GORJI H，EBRAHIMPOUR R，ZABBAH S.A temporal hierarchical feedforward model explains both the time and the accuracy of object recognition[J].Scientific Reports，2021，11（1）：5640.
[59] KHERADPISHEH S R，GANJTABESH M，MASQUELIER T.Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition[J].Neurocomputing，2016，205：382-392.
[60] FAGHIHI F，MOLHEM H，MOUSTAFA A A.Toward one-shot learning in neuroscience-inspired deep spiking neural networks[J/OL].[2021-10-19].https：//doi.org/10.1101/829556.
[61] LIU J X，HUO H，HU W T，et al.Brain-inspired hierarchical spiking neural network using unsupervised STDP rule for image classification[C]//Proceedings of 2018 10th International Conference on Machine Learning and Computing，2018：230-235.
[62] SONG S，MA C，YU Q.Brain-inspired framework for image classification with a new unsupervised matching pursuit encoding[C]//Proceedings of International Conference on Neural Information Processing，2020：208-219.
[63] LIANG Q，ZENG Y，XU B.Temporal-sequential learning with a brain-inspired spiking neural network and its application to musical memory[J].Frontiers in Computational Neuroscience，2020，14：51.
[64] DOBORJEH Z G，KASABOV N，DOBORJEH M G，et al.Modelling peri-perceptual brain processes in a deep learning spiking neural network architecture[J].Scientific Reports，2018，8：8912.
[65] DAN Y，POO M M.Spike timing-dependent plasticity of neural circuits[J].Neuron，2004，44（1）：23-30.
[66] SHADLEN M N，MOVSHON J A.Synchrony unbound：A critical evaluation of the temporal binding hypothesis[J].Neuron，1999，24（1）：67-77.
[67] VOGELS T P，RAJAN K，ABBOTT L F.Neural network dynamics[J].Annual Review of Neuroscience，2005，28：357-376.
[68] PEDRETTI G，MILO V，AMBROGIO S，et al.Memristive neural network for on-line learning and tracking with brain-inspired spike timing dependent plasticity[J].Scientific Reports，2017，7：5288.
[69] BERBERIAN N，ROSS M，CHARTIER S.Discrimination of motion direction in a robot using a phenomenological model of synaptic plasticity[J].Computational Intelligence and Neuroscience，2019（3）.
[70] DAVID S V，HAYDEN B Y，GALLANT J L.Spectral receptive field properties explain shape selectivity in area V4[J].Journal of Neurophysiology，2006，96（6）：3492-3505.
[71] WANG G，TANAKA K，TANIFUJI M.Optical imaging of functional organization in the monkey inferotemporal cortex[J].Science，1996，272：1665-1668.
[72] YAMANE Y，CARLSON E T，BOWMAN K C，et al.A neural code for three-dimensional object shape in macaque inferotemporal cortex[J].Nature Neuroscience，2008，11（11）：1352-1360.
[73] RIESENHUBER M，POGGIO T.Neural mechanisms of object recognition[J].Current Opinion in Neurobiology，2002，12（2）：162-168.
[74] ZEMAN A A，RITCHIE J B，BRACCI S，et al.Orthogonal representations of object shape and category in deep convolutional neural networks and human visual cortex[J].Scientific Reports，2020，10：2453.
[75] MOHSENZADEH Y，MULLIN C，LAHNER B，et al.Emergence of visual center-periphery spatial organization in deep convolutional neural networks[J].Scientific Reports，2020，10：4638.
[76] SEELIGER K，FRITSCHE M，GUCLU U，et al.Convolutional neural network-based encoding and decoding of visual object recognition in space and time[J].Neuroimage，2018，180：253-266.
[77] CICHY R M，KHOSLA A，PANTAZIS D，et al.Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence[J].Scientific Reports，2016，6：27755.
[78] CADIEU C F，HONG H，YAMINS D L K，et al.Deep neural networks rival the representation of primate it cortex for core visual object recognition[J].Plos Computational Biology，2014，10（12）：e1003963.
[79] AGRAWAL P，STANSBURY D，MALIK J，et al.Pixels to Voxels：Modeling visual representation in the human brain[J].arXiv：1407.5104，2014.
[80] DONG Q L，WANG H，HU Z Y.Statistics of visual responses to image object stimuli from primate AIT neurons to DNN neurons[J].Neural Computation，2018，30（2）：447-476.
[81] KUZOVKIN I，VICENTE R，PETTON M，et al.Activations of deep convolutional neural networks are aligned with Gamma band activity of human visual cortex[J].Communications Biology，2018，1：107.
[82] KAR K，KUBILIUS J，SCHMIDT K，et al.Evidence that recurrent circuits are critical to the ventral stream’s execution of core object recognition behavior[J].Nature Neuroscience，2019，22（6）：974.
[83] JACOB G，PRAMOD R T，KATTI H，et al.Qualitative similarities and differences in visual object representations between brains and deep networks[J].Nature Communications，2021，12（1）：1872.
[84] VINKEN K，BOIX X，KREIMAN G.Incorporating intrinsic suppression in deep neural networks captures dynamics of adaptation in neurophysiology and perception[J].Science Advances，2020，42：4205.
[85] SWIRSKY L T，MARINACCI R M，SPANIOL J.Reward anticipation selectively boosts encoding of gist for visual objects[J].Scientific Reports，2020，10：20196.
[86] HAN Y，ROIG G，GEIGER G，et al.Scale and translation-invariance for novel objects in human vision[J].Scientific Reports，2020，10：1411.
[87] HONG H，YAMINS D L K，MAJAJ N J，et al.Explicit information for category-orthogonal object properties increases along the ventral stream[J].Nature Neuroscience，2016，19（4）：613.
[88] SERRE T.Deep learning：The good，the bad，and the ugly[J].Annual Review of Vision Science，2019，5：399-426.
[89] RAJALINGHAM R，ISSAE B，BASHIVAN P，et al.Large-scale，high-resolution comparison of the core visual object recognition behavior of humans，monkeys，and state-of-the-art deep artificial neural networks[J].Journal of Neuroscience，2018，38：7255-7269.
[90] ULLMAN S，ASSIF L，FETAYA E，et al.Atoms of recognition in human and computer vision[J].Proceedings of the National Academy of Sciences of the United States of America，2016，113：2744-2749.
[91] KHERADPISHEH S R，GHODRATI M，GANJTABESH M，et al.Deep networks can resemble human feed-forward vision in invariant object recognition[J].Scientific Reports，2016，6：32672.
[92] PRAMOD R T，ARUN S P.Do computational models differ systematically from human object perception?[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition，2016：1601-1609.
[93] AYZENBERG V，LOURENCO S F.Skeletal descriptions of shape provide unique perceptual information for object recognition[J].Scientific Reports，2019，9：9359.
[94] SOLOMON S G，KOHN A.Moving sensory adaptation beyond suppressive effects in single neurons[J].Current Biology，2014，24：1012-1022.
[95] ASHBY E G，MADDOX W T.Human category learning[J].Annual Review of Psychology，2005，56：149-178.
[96] ANDRESEN D R，VINBERG J，GRILL-SPECTOR K.The representation of object viewpoint in human visual cortex[J].Neuroimage，2009，45（2）：522-536.
[97] COX D，MEYERS E，SINHA P.Contextually evoked object-specific responses in human visual cortex[J].Science，2004，304：115-117.
[98] BONE M B，AHMAD F，BUCHSBAUM B R.Feature- specific neural reactivation during episodic memory[J].Nature Communications，2020，11：1945.
[99] LEVY I，HASSON U，AVIDAN G，et al.Center-periphery organization of human object areas[J].Nature Neuroscience，2001，4（5）：533-539.
[100] MACEVOY S P，EPSTEIN R A.Constructing scenes from objects in human occipitotemporal cortex[J].Nature Neuroscience，2011，14（10）：1323.
[101] CICHY R M，PANTAZIS D，OLIVA A.Resolving human object recognition in space and time[J].Nature Neuroscience，2014，17（3）：455-462.
[102] LANDI S M，FREIWALD W A.Two areas for familiar face recognition in the primate brain[J].Science，2017，357：591-595.
[103] GEORGE D，LEHRACH W，KANSKY K，et al.A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs[J].Science，2017，358：2612.
[104] ZHAO F F，KONG Q Q，ZENG Y，et al.A brain-inspired visual fear responses model for UAV emergent obstacle dodging[J].IEEE Transactions on Cognitive and Developmental Systems，2020，12（1）：124-132.
[105] OKAMURA J Y，YAMAGUCHI R，HONDA K，et al.Neural substrates of view-invariant object recognition developed without experiencing rotations of the objects[J].Journal of Neuroscience，2014，34：15047-15059.
[106] GAVORNIK J P，BEAR M F.Learned spatiotemporal sequence recognition and prediction in primary visual cortex[J].Nature Neuroscience，2014，17（5）：732.
[107] KONEN C S，KASTNER S.Two hierarchically organized neural systems for object information in human visual cortex[J].Nature Neuroscience，2008，11（2）：224-231.
[108] KAR K，DICARLO J J.Fast recurrent processing via ventrolateral prefrontal cortex is needed by the primate ventral stream for robust core visual object recognition[J].Neuron，2021，109（1）：164-176.
[109] BRADY T F，KONKLE T，ALVAREZ G A，et al.Visual long-term memory has a massive storage capacity for object details[J].Proceedings of the National Academy of Sciences of the United States of America，2008，105：14325-14329.
[110] PONCE C R，XIAO W，SCHADE P F，et al.Evolving images for visual neurons using a deep generative network reveals coding principles and neuronal preferences[J].Cell，2019，177（4）：999.
[111] COGGAN D D，LIU W L，BAKER D H，et al.Category-selective patterns of neural response in the ventral visual pathway in the absence of categorical information[J].Neuroimage，2016，135：107-114.
[112] LANGNER O，DOTSCH R，BIJLSTRA G，et al.Presentation and validation of the radboud faces database[J].Cognition and Emotion，2010，24（8）：1377-1388.
[113] LAUER T，CORNELISSEN T H W，DRASCHKOW D，et al.The role of scene summary statistics in object recognition[J].Scientific Reports，2018，8：14666.
[114] PEELEN M V，FEI-FEI L，KASTNER S.Neural mechanisms of rapid natural scene categorization in human visual cortex[J].Nature，2009，460：94-105.
[115] RUSSELL B C，TORRALBA A，MURPHY K P，et al.LabelMe：A database and web-based tool for image annotation[J].International Journal of Computer Vision，2008，77（1/3）：157-173.
[116] ORLOV T，ZOHARY E.Object representations in human visual cortex formed through temporal integration of dynamic partial shape views[J].Journal of Neuroscience，2018，38（3）：659-678.
[117] GIELIS J.A generic geometric transformation that unifies a wide range of natural and abstract shapes[J].American Journal of Botany，2003，90（3）：333-338.
[118] PODVALNY E，FLOUNDERS M W，KING L E，et al.A dual role of peristimulus spontaneous neural activity in visual object recognition[J].Nature Communications，2019，10：3910.
[119] DONIGER G M，FOXE J J，SCHROEDER C E，et al.Visual perceptual learning in human object recognition areas：A repetition priming study using high-density electrical mapping[J].Neuroimage，2001，13（2）：305-313.
[120] RUPP K，ROOS M，MILSAP G，et al.Semantic attributes are encoded in human electrocorticographic signals during visual object recognition[J].Neuroimage，2017，148：318-329.
[121] THOMA V，HENSON R N.Object representations in ventral and dorsal visual streams：fMRI repetition effects depend on attention and part-whole configuration[J].Neuroimage，2011，57（2）：513-525.
[122] SEHATPOUR P，MOLHOLM S，JAVITT D C，et al.Spatiotemporal dynamics of human object recognition processing：An integrated high-density electrical mapping and functional imaging study of “closure” processes[J].Neuroimage，2006，29（2）：605-618.
[123] SNODGRASS J G，VANDERWART M.A standardized set of 260 pictures：Norms for name agreement，image agreement，familiarity，and visual complexity[J].Journal of Experimental Psychology，1980，62：174-215.
[124] GODDARD E，CARLSON T A，DERMODY N，et al.Representational dynamics of object recognition：Feedforward and feedback information flows[J].Neuroimage，2016，128：385-397.
[125] KRIEGESKORTE N，MUR M，RUFF D A，et al.Matching categorical object representations in inferior temporal cortex of man and monkey[J].Neuron，2008，60（6）：1126-1141.
[126] LIN T Y，MAIRE M，BELONGIE S，et al.Microsoft COCO：Common objects in context[C]//Proceedings of International Conference on Computer Vision，2014：740-755.
[127] KAPOOR A，SHENOY P，TAN D.Combining brain computer interfaces with vision for object categorization[C]//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition，2008.
[128] GRIFFIN G，HOLUB A，PERONA P.Caltech-256 object category dataset：CalTech Report[R].2007.
[129] CADIEU C，HONG H，YAMINS D，et al.The neural representation benchmark and its evaluation on brain and machine[J].arXiv：1301.3530，2013.
[130] DENG J，DONG W，SOCHER R，et al.ImageNet：AL[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition，2009：248-255.
[131] HORIKAWA T，KAMITANI Y.Generic decoding of seen and imagined objects using hierarchical visual features[J].Nature Communications，2017，8：15037.
[132] LI F F，FERGUS R，PERONA P.Learning generative visual models from few training examples：An incremental Bayesian approach tested on 101 object categories[J].Computer Vision and Image Understanding，2007，106（1）：59-70.
[133] KRIZHEVSKY A，HINTON G.Learning multiple layers of features from tiny images[J].Handbook of Systemic Autoimmune Diseases，2009，1（4）：3-58.
[134] KATTI H，ARUN S P.Are you from northor south India? A hard face-classification task reveals systematic representational differences between humans and machines[J].Journal of Vision，2019，19（7）：1-17.
[135] BRODEUR M B，DIONNE-DOSTIE E，MONTREUIL T，et al.The bank of standardized stimuli（BOSS），a new set of 480 normative photos of objects to be used as visual stimuli in cognitive research[J].Plos One，2010，5（5）：e10773.
[136] GEUSEBROEK J M，BURGHOUTS G J，SMEULDERS A W M.The amsterdam library of object images[J].International Journal of Computer Vision，2005，61（1）：103-112.
[137] EVERINGHAM M，VAN GOOL L，WILLIAMS C K I，et al.The pascal visual object classes（VOC） challenge[J].International Journal of Computer Vision，2010，88（2）：303-338.
[138] XIAO J X，HAYS J，EHINGER K A，et al.SUN database：Large-scale scene recognition from abbey to zoo[C]//Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition，2010：3485-3492.
[139] STAAL J，ABRAMOFF M D，NIEMEIJER M，et al.Ridge-based vessel segmentation in color images of the retina[J].IEEE Transactions on Medical Imaging，2004，23（4）：501-509.
[140] HOOVER A，KOUZNETSOVA V，GOLDBAUM M.Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response[J].IEEE Transactions on Medical Imaging，2000，19（3）：203-210.
[141] GRIGORESCU C，PETKOV N.Distance sets for shape filters and shape recognition[J].IEEE Transactions on Image Processing，2003，12（10）：1274-1286.
[142] LECUN Y，CORTES C.The MNIST database of handwritten digits[EB/OL].[2021-10-19].http：//yann.lecun.com/exdb/mnist/.
[143] DOSOVITSKIY A，FISCHER P，ILG E，et al.FlowNet：Learning optical flow with convolutional networks[C]//Proceedings of 2015 IEEE International Conference on Computer Vision，2015：2758-2766.
[144] BUTLER D J，WULFF J，STANLEY G B，et al.A naturalistic open source movie for optical flow evaluation[C]//Proceedings of IEEE International Conference on Computer Vision，2012：611-625.
[145] GEIGER A，LENZ P，URTASUN R.Are we ready for autonomous driving？The KITTI vision benchmark suite[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition，2012：3354-3361.
[146] MENZE M，GEIGER A.Object scene flow for autonomous vehicles[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition，2015：3061-3070.
[147] NETZER Y，WANG T，COATES A，et al.Reading digits in natural images with unsupervised feature learning[J].NIPS，2011，49：1-9.
[148] SAVARESE S，LI F F.3D generic object categorization，localization and pose estimation[C]//Proceedings of 2007 IEEE 11th International Conference on Computer Vision，2007：1-8.
[149] LEIBE B，SCHIELE B.Analyzing appearance and contour based methods for object categorization[C]//Proceedings of 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2003：409.
[150] HUANG G B，MATTAR M A，LEE H，et al.Learning to align from scratch[C]//Advances in Neural Information Processing Systems，2012：764-772.
[151] KAY K N，NASELARIS T，PRENGER R J，et al.Identifying natural images from human brain activity[J].Nature，2008，452：352-355.
[152] NISHIMOTO S，VU A T，NASELARIS T，et al.Reconstructing visual experiences from brain activity evoked by natural movies[J].Current Biology，2011，21（19）：1641-1646.
[153] RITCHIE J B，DE BEECK H.Using neural distance to predict reaction time for categorizing the animacy，shape，and abstract properties of objects[J].Scientific Reports，2019，9：13201.
[154] BRACCI S，DE BEECK H.Dissociations and associations between shape and category representations in the two visual pathways[J].Journal of Neuroscience，2016，36（2）：432-444.
[155] ZHOU B L，LAPEDRIZA A，KHOSLA A，et al.Places：A 10 million image database for scene recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2018，40（6）：1452-1464.
[156] ROSCH E.Basic objects in natural categories[J].Bulletin of the Psychonomic Society，1975，6：415.
[157] DE LANDETA A B，PEREYRA M，MEDINA J H，et al.Anterior retro splenial cortex is required for long-term object recognition memory[J].Scientific Reports，2020，10：4002.
[158] TODD J J，MAROIS R.Capacity limit of visual short-term memory in human posterior parietal cortex[J].Nature，2004，428：751-754.
[159] MICELI G，FOUCH E，CAPASSO R，et al.The dissociation of color from form and function knowledge[J].Nature Neuroscience，2001，4（6）：662-667.
[160] KOURTZI Z，KANWISHER N.Representation of perceived object shape by the human lateral occipital complex[J].Science，2001，293：1506-1509.
[161] GRILL-SPECTOR K，KUSHNIR T，HENDLER T，et al.The dynamics of object-selective activation correlate with recognition performance in humans[J].Nature Neuroscience，2000，3（8）：837-843.
[162] DOWNING P E，JIANG Y H，SHUMAN M，et al.A cortical area selective for visual processing of the human body[J].Science，2001，293：2470-2473.
[163] REES G，FRACKOWIAK R，FRITH C.Two modulatory effects of attention that mediate object categorization in human cortex[J].Science，1997，275：835-838.
[164] LI N，DICARLO J J.Unsupervised natural experience rapidly alters invariant object representation in visual cortex[J].Science，2008，321：1502-1507.
[165] TAKEUCHI D，HIRABAYASHI T，TAMURA K，et al.Reversal of interlaminar signal between sensory and memory processing in monkey temporal cortex[J].Science，2011，331：1443-1447.
[166] BICHOT N P，ROSSI A F，DESIMONE R.Parallel and serial neural mechanisms for visual search in macaque area V4[J].Science，2005，308：529-534.
[167] KOSSE C，BURDAKOV D.Natural hypothalamic circuit dynamics underlying object memorization[J].Nature Communications，2019，10：2505.
[168] LOPEZ-ARANDA M F，LOPEZ-TELLEZ J F，NAVARRO-LOBATO I，et al.Role of layer 6 of V2 visual cortex in object-recognition memory[J].Science，2009，325：87-89.
[169] TENENBAUM J B，KEMP C，GRIFFITHS T L，et al.How to grow a mind：Statistics，structure，and abstraction[J].Science，2011，331：1279-1285.