CoChat
Sign Up
Cited by 16Advanced Neural Network ApplicationsVisual Attention and Saliency DetectionVisual perception and processing mechanisms

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Are there any ‘object detectors’ in the hidden layers of CNNs trained to identify objects or scenes?

Open access
Gale, Ella M., Martin, Nicholas, Blything, Ryan, Nguyen, Anh, Bowers, Jeffrey S.·2020·Vision Research
DOI 10.1016/j.visres.2020.06.007
Open this paper in CoChat — free accountOpen PDF

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.visres.2020.06.007

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The highly activating data set examples method relies on human prior beliefs, which may lead interpreters to project their human understanding onto models that may be using unfamiliar concepts.

    “The first issue is that the method relies on human prior beliefs, which may lead interpreters to project their human understanding onto models that may, in fact, be using unfamiliar concepts.”

    From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Gale et al., 2020

    Section 3.12 describes asking people to identify a common object in image panels, and Section 4.2 finds that human interpretations of activation-maximization images do not necessarily indicate unit selectivity. This supports a caution about relying on human interpretation, but the paper does not say that interpreters project prior beliefs onto models using unfamiliar concepts. Page numbers were not available in our copy. (LLM, conf=0.77)

    Experimental — accuracy not yet measured

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

Flagged first, then by citations

Research works printed but not linked: 36

  1. Bau, D., Zhu, J.-Y., Strobelt, H., Zhou, B., Tenenbaum, J.B., Freeman, W.T. & Torralba, A., 2019. Visualizing and understanding generative adversarial networks. In: International Conference on Learning Representations. https://openreview.net/forum?id=Hyg_X2C5FX.
  2. Berkeley, 1995, Density plots of hidden value unit activations reveal interpretable bands, Connection Science, 7, 167, 10.1080/09540099550039336 · DOI
  3. Bowers, 2009, On the biological plausibility of grandmother cells: implications for neural network theories in psychology and neuroscience, Psychological Review, 116, 220, 10.1037/a0014462 · DOI
  4. Bowers, 2010, More on grandmother cells and the biological implausibility of PDP models of cognition: A reply to Plaut and McClelland (2010) and Quian Quiroga and Kreiman (2010), Psychological Review, 117, 300, 10.1037/a0018047 · DOI
  5. Bowers, 2017, Grandmother cells and localist representations: A review of current thinking, Language, Cognition, and Neuroscience, 257, 10.1080/23273798.2016.1267782 · DOI
  6. Bowers, 2014, Neural networks learn highly selective representations in order to overcome the superposition catastrophe, Psychological Review, 121, 248, 10.1037/a0035943 · DOI
  7. Bowers, 2016, Why do some neurons in cortex respond to information in a selective manner? Insights from artificial neural networks, Cognition, 148, 47, 10.1016/j.cognition.2015.12.009 · DOI
  8. Bowers, 2019, Researchers Keep Rejecting Grandmother Cells after Running the Wrong Experiments: The Issue Is How Familiar Stimuli Are Identified, BioEssays, 41, 10.1002/bies.201800248 · DOI
  9. Burgess, C. P., Higgins, I., Pal, A., Matthey, L., Watters, N., Desjardins, G., & Lerchner, A. (2018). Understanding disentangling in β-VAE. arXiv preprint arXiv:1804.03599, 2018. · arXiv
  10. Erhan, 2009, Visualizing higher-layer features of a deep network, University of Montreal, 1341, 1
  11. Gubian, 2017, Comparing single-unit recordings taken from a localist model to single-cell recording data: a good match, Language, Cognition and Neuroscience, 32, 380, 10.1080/23273798.2016.1259482 · DOI
  12. Han, 2017, Pre-trained alexnet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification, Remote Sensing, 9, 848, 10.3390/rs9080848 · DOI
  13. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093. · DOI · Paper page
  14. Karpathy, A., Johnson, J., & Fei-Fei, L. (2016). Visualizing and understanding recurrent networks. In: Workshop Track at International Conference on Learning Representations.
  15. Kubilius, J., Schrimpf, M., Nayebi, A., Bear, D., Yamins, D.L., & DiCarlo, J.J. (2018). Cornet: modeling the neural mechanisms of core object recognition. BioRxiv, page 408385. · DOI
  16. Lakretz, Y., Kruszewski, G., Desbordes, T., Hupkes, D., Dehaene, S., & Baroni, M. (2019). The emergence of number and syntax units in lstm language models. arXiv preprint arXiv:1903.07435. · DOI
  17. Leavitt, M. L. & Morcos, A. (2020). Selectivity considered harmful: evaluating the causal impact of class selectivity in dnns. arXiv preprint arXiv:2003.01262. · arXiv
  18. Morcos, A. S., Barrett, D. G., Rabinowitz, N. C., & Botvinick, M. (2018). On the importance of single directions for generalization. In: International Conference on Learning Representations. https://openreview.net/forum?id=r1iuQjxCZ.
  19. Na, S., Choe, Y. J., Lee, D. -H., Kim, G. (2019). Discovery of natural language concepts in individual units of cnns. In: International Conference on Learning Representations. https://openreview.net/forum?id=S1EERs09YQ.
  20. Nguyen, A., Dosovitskiy, A., Yosinski, J., Brox, T., & Clune, J. (2013). Synthesizing the preferred inputs for neurons in neural networks via deep generator networks. In: Advances in Neural Information Processing Systems, pages 3387–3395, 2016.
  21. Nguyen, A., Yosinski, J., & Clune, J. (2016). Multifaceted feature visualization: Uncovering the different types of features learned by each neuron in deep neural networks. arXiv preprint arXiv:1602.03616. · arXiv
  22. Nguyen, A., Yosinski, J., Clune, J. (2019). Understanding neural networks via feature visualization: A survey. arXiv preprint arXiv:1904.08939, 2019. · DOI
  23. Plaut, D.C. & McClelland, J.L. (2010). Locating object knowledge in the brain: Comment on Bowers’s (2009) attempt to revive the grandmother cell hypothesis. Psychological Review, 117 (1): 284–288. ISSN 1939–1471. doi: 10.1037/a0017101. URL papers3://publication/doi/10.1037/a0017101. · DOI
  24. Powers, 2011, Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation, Journal of Machine Learning Technologies
  25. Quian Quiroga, R. & Kreiman, R. (2010). Measuring Sparseness in the Brain: Comment on Bowers (2009). Psychological Review. · DOI
  26. Quiroga, 2016, Neuronal codes for visual perception and memory, Neuropsychologia, 83, 227, 10.1016/j.neuropsychologia.2015.12.016 · DOI
  27. Radford, A., Jozefowicz, R., & Sutskever, I. (2017). Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444. · arXiv
  28. Riesenhuber, 2002, How visual cortex recognizes objects: The tale of the standard model, The Visual Neurosciences
  29. Simonyan, K., Vedaldi, A. & Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034. · arXiv
  30. Yamins, 2014, Performance-optimized hierarchical models predict neural responses in higher visual cortex, Proceedings of the National Academy of Sciences, 111, 8619, 10.1073/pnas.1403112111 · DOI · Paper page
  31. Yosinski, J., Clune, J., Nguyen, A., Fuchs, T. & Lipson, H. (2015). Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579. · arXiv
  32. Yosinski, J., Clune, J., Nguyen, A., Fuchs, T. & Lipson, H. (2015). Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579. · arXiv
  33. Zhou, B., Lapedriza, A., Xiao, J., Torralba, A. & Oliva, A. (2014). Learning deep features for scene recognition using places database. In: Advances in neural information processing systems, pages 487–495.
  34. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A. (2015). Object detectors emerge in deep scene CNNs. In: International Conference on Learning Representations.
  35. Zhou, 2018, Interpreting deep visual representations via network dissection, IEEE Transactions on Pattern Analysis and Machine Intelligence
  36. Zhou, B., Sun, Y., Bau, D., & Torralba, A. (2018). Revisiting the importance of individual units in CNNs via ablation. arXiv preprint arXiv:1806.02891. · arXiv

Cited by

Sorted by citations

Metadata

Authors
Gale, E. M., Martin, N., Blything, R., Nguyen, A., & Bowers, J. S.
Affiliations
  • University of Bristol (GB)
  • Auburn University (US)
Corresponding author
  • Martin, Nicholas
  • Bowers, Jeffrey S.
ORCID
Venue
Vision Research
Publisher
Elsevier BV
Published
2020-11
Volume
176
Pages
60-71
ISSN
0042-6989 (ISSN-L)
DOI
10.1016/j.visres.2020.06.007
OpenAlex
W2997297949
Cited by
16
References
3
Citations by year
2025: 3 · 2024: 5 · 2023: 3 · 2022: 2 · 2021: 3
FWCI
0.67
Type
journal article
Language
en
Open access
Licence
Locations
  • Vision Research (publishedVersion)
  • PubMed (publishedVersion)
  • Explore Bristol Research (publishedVersion, cc-by-nc-nd)
  • Bristol Research (University of Bristol) (publishedVersion, cc-by-nc-nd)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Science Foundation (1850117)
  • Horizon 2020
  • Leverhulme Trust (RPG-2016\u2013113, 113, RPG-2016)
  • European Research Council
  • Horizon 2020 Framework Programme (741134)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Visual perception and processing mechanisms
Keywords
object selectivity, object detectors, hidden layer neurons, signal detection, activation maximization, AlexNet, VGG16, GoogLeNet, precision, false alarm rate, hit rate, grandmother cells, object classification, image classification
MeSH terms
Humans, Neural Networks, Computer

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