Beyond the feedforward sweep: feedback computations in the visual cortex
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
Visual perception involves the rapid formation of a coarse image representation at the onset of visual processing, which is iteratively refined by late computational processes. These early versus late time windows approximately map onto feedforward and feedback processes, respectively. State‐of‐the‐art convolutional neural networks, the main engine behind recent machine vision successes, are feedforward architectures. Their successes and limitations provide critical information regarding which visual tasks can be solved by purely feedforward processes and which require feedback mechanisms. We provide an overview of recent work in cognitive neuroscience and machine vision that highlights the possible role of feedback processes for both visual recognition and beyond. We conclude by discussing important open questions for future research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Complex networks: structure and dynamics
BOCCALETTI, S., LATORA, V, MORENO, Y., CHAVEZ, M., & HWANG, D. (2006) · Physics Reports · doi:10.1016/j.physrep.2005.10.009 · Cited by 11,010
Mental Rotation of Three-Dimensional Objects
Shepard, R. N., & Metzler, J. (1971) · Science · doi:10.1126/science.171.3972.701 · Cited by 6,246
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
Fukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759 · cited 1×
“14,17,18 Starting with Fukushima’s neocognitron, 19 computational models constrained by the anatomy and physiology of the visual cortex (VC) (see Refs.”
BackgroundRao, R. P. N., & Ballard, D. H. (1999) · Nature Neuroscience · doi:10.1038/4580 · Cited by 5,483 · cited 1×
“157,158 159–162 Common to many of these models is the notion that feedback signals provide a prediction of what will transpire next while the feedforward signals convey an error, or difference, between those predictions and the incoming inputs.”
BackgroundResidual Attention Network for Image Classification
Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., & Tang, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.683 · Cited by 4,073
Energy and Policy Considerations for Deep Learning in NLP
Strubell, E., Ganesh, A., & McCallum, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1355 · Cited by 3,684
Speed of processing in the human visual system
Thorpe, S., Fize, D., & Marlot, C. (1996) · Nature · doi:10.1038/381520a0 · Cited by 3,538
Hierarchical models of object recognition in cortex
Riesenhuber, M., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/14819 · Cited by 3,309 · cited 1×
“20–22 for reviews) account relatively well for this pattern of behavioral responses.”
BackgroundUnderstanding deep learning requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016) · arXiv · doi:10.48550/arxiv.1611.03530 · Cited by 2,838 · cited 2×
“This idea was used by Recht et al. 75 who confirmed that modern deep network architectures could achieve near-perfect training accuracy using random labels.”
MethodCanonical Microcircuits for Predictive Coding
Bastos, A. M., Usrey, W. M., Adams, R. A., Mangun, G. R., Fries, P., & Friston, K. J. (2012) · Neuron · doi:10.1016/j.neuron.2012.10.038 · Cited by 2,421 · cited 1×
“157,158 159–162 Common to many of these models is the notion that feedback signals provide a prediction of what will transpire next while the feedforward signals convey an error, or difference, between those predictions and the incoming inputs.”
BackgroundThe distinct modes of vision offered by feedforward and recurrent processing
Lamme, V. A. F., & Roelfsema, P. R. (2000) · Trends in Neurosciences · doi:10.1016/s0166-2236(00)01657-x · Cited by 2,338 · cited 1×
“…patterns of connectivity, in turn, constrain visual processing dynamics to be roughly composed of an early “bottom-up phase” primarily carried by feedfor-ward processes during the first 150 ms after visual onset followed by a late “reentrant” phase carried by feedback processes 5 (but see also Ref.”
BackgroundMaking the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., & Parikh, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.670 · Cited by 2,287
Performance-optimized hierarchical models predict neural responses in higher visual cortex
Yamins, D. L. K., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1403112111 · Cited by 1,924
How to grow a mind: Statistics, structure, and abstraction
Tenenbaum, J. B., Kemp, C., Griffiths, T. L., & Goodman, N. D. (2011) · Science · doi:10.1126/science.1192788 · Cited by 1,815
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.215 · Cited by 1,781
Invariant Scattering Convolution Networks
Bruna, J., & Mallat, S. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.230 · Cited by 1,633
Hochstein (2002) · doi:10.1016/s0896-6273(02)01091-7 · Cited by 1,397
Top-down influences on visual processing
Gilbert, C. D., & Li, W. (2013) · Nature Reviews Neuroscience · doi:10.1038/nrn3476 · Cited by 1,224
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale
Kemelmacher-Shlizerman, I., Seitz, S. M., Miller, D., & Brossard, E. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.527 · Cited by 912
A Weighted and Directed Interareal Connectivity Matrix for Macaque Cerebral Cortex
Markov, N. T., Ercsey-Ravasz, M. M., Ribeiro Gomes, A. R., Lamy, C., Magrou, L., Vezoli, J., Misery, P., Falchier, A., Quilodran, R., Gariel, M. A., et al. (2014) · Cerebral Cortex · doi:10.1093/cercor/bhs270 · Cited by 857 · cited 1×
“1,3,4 Such patterns of connectivity, in turn, constrain visual processing dynamics to be roughly composed of an early “bottom-up phase” primarily carried by feedfor-ward processes during the first 150 ms after visual onset followed by a late “reentrant” phase carried by feedback processes 5 (but…”
BackgroundFast Readout of Object Identity from Macaque Inferior Temporal Cortex
Hung, C. P., Kreiman, G., Poggio, T., & DiCarlo, J. J. (2005) · Science · doi:10.1126/science.1117593 · Cited by 854
Self-citationCadieu, C. F., Hong, H., Yamins, D. L. K., Pinto, N., Ardila, D., Solomon, E. A., Majaj, N. J., & DiCarlo, J. J. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003963 · Cited by 824 · cited 1×
“Although these network models are not constrained by experimental data, they have nonetheless been shown to provide an even better fit than earlier models to both behavioral 18,24,25 and electrophysiological 26,27 data (but see Ref.”
Kar, K., Kubilius, J., Schmidt, K., Issa, E. B., & DiCarlo, J. J. (2019) · Nature Neuroscience · doi:10.1038/s41593-019-0392-5 · Cited by 496 · cited 2×
“15 Recurrent computations are not only relevant for recognition, but they can also help solve other problems.”
BackgroundNeural mechanisms of selective visual attention.
Moore, T., & Zirnsak, M. (2017) · Annual Review of Psychology · doi:10.1146/annurev-psych-122414-033400 · Cited by 471
Masking Disrupts Reentrant Processing in Human Visual Cortex
Fahrenfort, J. J., Scholte, H. S., & Lamme, V. A. F. (2007) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.2007.19.9.1488 · Cited by 344
Masking Interrupts Figure-Ground Signals in V1
Lamme, V. A. F., Zipser, K., & Spekreijse, H. (2002) · Journal of Cognitive Neuroscience · doi:10.1162/089892902320474490 · Cited by 285
A source for feature-based attention in the prefrontal cortex
Bichot, N. P., Heard, M. T., DeGennaro, E. M., & Desimone, R. (2015) · Neuron · doi:10.1016/j.neuron.2015.10.001 · Cited by 283
Hamker, F. H. (2005) · Cerebral Cortex · doi:10.1093/cercor/bhh146 · Cited by 217
The modular organization of projections from areas V1 and V2 to areas V4 and TEO in macaques
Nakamura, H., Gattass, R., Desimone, R., & Ungerleider, L. (1993) · The Journal of Neuroscience · doi:10.1523/jneurosci.13-09-03681.1993 · Cited by 211 · cited 1×
“1 A related way to achieve flexibility is through bypass routes [40], which allow the architecture to skip some of the processing stages [19], and which may help alleviate the issue of a fixed architecture to some extent (at the expense of adding and training yet more connections).”
BackgroundThe implementation of visual routines
Roelfsema, P. R., Lamme, V. A. F., & Spekreijse, H. (2000) · Vision Research · doi:10.1016/s0042-6989(00)00004-3 · Cited by 162 · cited 2×
“6 and 35 for reviews; see also Ref.”
BackgroundA neural network trained for prediction mimics diverse features of biological neurons and perception
Lotter, W., Kreiman, G., & Cox, D. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0170-9 · Cited by 128
Self-citationReappraising the functional implications of the primate visual anatomical hierarchy.
Hegdé, J., & Felleman, D. J. (2007) · The Neuroscientist · doi:10.1177/1073858407305201 · Cited by 78 · cited 1×
“58 Yet, this approximate separation of temporal scales has been useful to conceptualize and understand the sequence of computations that ultimately lead to visual cognition.”
BackgroundSinha, P. (2002) · Nature Neuroscience · doi:10.1038/nn949 · Cited by 65
Deep Predictive Learning: A Comprehensive Model of Three Visual Streams
O'Reilly, R. C., Wyatte, D. R., & Rohrlich, J. (2017) · arXiv · doi:10.48550/arxiv.1709.04654 · Cited by 26
Cited by
Perirhinal input to neocortical layer 1 controls learning
Doron, G., Shin, J. N., Takahashi, N., Drüke, M., Bocklisch, C., Skenderi, S., de Mont, L., Toumazou, M., Ledderose, J., Brecht, M., et al. (2020) · Science · doi:10.1126/science.aaz3136 · Cited by 160
“Our data therefore imply that medial-temporal– dependent learning predominantly involves the plasticity of internally generated feedback signals, which would have ramifications not only for our understanding of the brain but also for the principles of learning in artificial recurrent neural networks (51).”
BackgroundTheory of the Multiregional Neocortex: Large-Scale Neural Dynamics and Distributed Cognition
Wang, X.-J. (2022) · Annual Review of Neuroscience · doi:10.1146/annurev-neuro-110920-035434 · Cited by 83
Predictive coding with spiking neurons and feedforward gist signaling
Lee, K., Dora, S., Mejias, J. F., Bohte, S. M., & Pennartz, C. M. A. (2024) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2024.1338280 · Cited by 14
“While the precise contributions of feedforward and recurrent processes to perception are yet to be determined (Kreiman and Serre, 2020), we aimed to combine these two temporally distinct processes by integrating the FFG pathway in a PC architecture and asked whether the FFG pathway can improve…”
BackgroundWu (2021) · doi:10.1523/eneuro.0267-20.2020 · Cited by 6
“…visual search and related tasks (e.g., instance segmentation) also employ attentional or recurrent mechanisms (Linsley et al., 2020), supporting the hypothesis that convolutional feedforward networks can benefit from recurrent mechanisms in solving visual reasoning tasks (Kreiman and Serre, 2020).”
BackgroundSingle-neuron encoding of rapidly learned visual information reshapes human perception
Armendariz, M., Blumberg, J., Singer, J., Aiple, F., Kim, J., Domínguez-Iturza, N., Brandt, A., Reinacher, P., Schulze-Bonhage, A., & Kreiman, G. (2026) · Nature Neuroscience · doi:10.1038/s41593-026-02496-6
Self-citation
Metadata
- Authors
- Kreiman, G., & Serre, T.
- Venue
- Annals of the New York Academy of Sciences
- Publisher
- Wiley
- Published
- 2020-02-28
- Volume
- 1464
- Issue
- 1
- Pages
- 222-241
- ISSN
- 0077-8923 (ISSN-L)
- 1749-6632
- OpenAlex
- W3008289458
- Cited by
- 83
- References
- 38
- FWCI
- 5.26
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.