Not-So-CLEVR: learning same–different relations strains feedforward neural networks
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
The advent of deep learning has recently led to great successes in various engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural network, now approach human accuracy on visual recognition tasks like image classification and face recognition. However, here we will show that feedforward neural networks struggle to learn abstract visual relations that are effortlessly recognized by non-human primates, birds, rodents and even insects. We systematically study the ability of feedforward neural networks to learn to recognize a variety of visual relations and demonstrate that same–different visual relations pose a particular strain on these networks. Networks fail to learn same–different visual relations when stimulus variability makes rote memorization difficult. Further, we show that learning same–different problems becomes trivial for a feedforward network that is fed with perceptually grouped stimuli. This demonstration and the comparative success of biological vision in learning visual relations suggests that feedback mechanisms such as attention, working memory and perceptual grouping may be the key components underlying human-level abstract visual reasoning.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Mental Rotation of Three-Dimensional Objects
Shepard, R. N., & Metzler, J. (1971) · Science · doi:10.1126/science.171.3972.701 · Cited by 6,246
Connectionism and cognitive architecture: A critical analysis
Fodor, J. A., & Pylyshyn, Z. W. (1988) · Cognition · doi:10.1016/0010-0277(88)90031-5 · Cited by 4,022
Human-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817
Signature Verification Using A "Siamese" Time Delay Neural Network
BROMLEY, J., BENTZ, J. W., BOTTOU, L., GUYON, I., LECUN, Y., MOORE, C., SÄCKINGER, E., & SHAH, R. (1993) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001493000339 · Cited by 2,077
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
Cited by
Organoid intelligence (OI): the new frontier in biocomputing and intelligence-in-a-dish
Smirnova, L., Caffo, B. S., Gracias, D. H., Huang, Q., Morales Pantoja, I. E., Tang, B., Zack, D. J., Berlinicke, C. A., Boyd, J. L., Harris, T. D., et al. (2023) · Frontiers in Science · doi:10.3389/fsci.2023.1017235 · Cited by 276
Deep Learning: The Good, the Bad, and the Ugly
Serre, T. (2019) · Annual Review of Vision Science · doi:10.1146/annurev-vision-091718-014951 · Cited by 267
Self-citationPerformance vs. competence in human–machine comparisons
Firestone, C. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1905334117 · Cited by 150
On the Binding Problem in Artificial Neural Networks
Greff, K., van Steenkiste, S., & Schmidhuber, J. (2020) · arXiv · doi:10.48550/arxiv.2012.05208 · Cited by 102
“(d) Neural networks also struggle to learn visual relations such as whether two shapes are the same or different (Fleuret et al., 2011; Kim et al., 2018).”
BackgroundWu (2021) · doi:10.1523/eneuro.0267-20.2020 · Cited by 6
Metadata
- Authors
- Kim, J., Ricci, M., & Serre, T.
- Venue
- Interface Focus
- Publisher
- The Royal Society
- Published
- 2018-01-06
- Volume
- 8
- Issue
- 4
- Pages
- 20180011-20180011
- ISSN
- 2042-8898 (ISSN-L)
- 2042-8901
- OpenAlex
- W2808580750
- Cited by
- 103
- References
- 20
- FWCI
- 4.01
- Type
- journal article
- Language
- en
- Open access
- bronze
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.