Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 496

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Visualizing Deep Convolutional Neural Networks Using Natural Pre-images

Open access
Mahendran, Aravindh, Vedaldi, Andrea·2016·International Journal of Computer Vision
DOI 10.1007/s11263-016-0911-8
Open this paper in CoChat — free account

Abstract

Image representations, from SIFT and bag of visual words to convolutional neural networks (CNNs) are a crucial component of almost all computer vision systems. However, our understanding of them remains limited. In this paper we study several landmark representations, both shallow and deep, by a number of complementary visualization techniques. These visualizations are based on the concept of “natural pre-image”, namely a natural-looking image whose representation has some notable property. We study in particular three such visualizations: inversion, in which the aim is to reconstruct an image from its representation, activation maximization, in which we search for patterns that maximally stimulate a representation component, and caricaturization, in which the visual patterns that a representation detects in an image are exaggerated. We pose these as a regularized energy-minimization framework and demonstrate its generality and effectiveness. In particular, we show that this method can invert representations such as HOG more accurately than recent alternatives while being applicable to CNNs too. Among our findings, we show that several layers in CNNs retain photographically accurate information about the image, with different degrees of geometric and photometric invariance.

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 · 10.1007/s11263-016-0911-8

Cites

19 of 19 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

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

Show all 19 references

Research works printed but not linked: 31

  1. Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014). Return of the devil in the details: Delving deep into convolutional nets. In Proceedings of BMVC. · DOI · Paper page
  2. Chen, Y., Ranftl, R., & Pock, T. (2014). A bi-level view of inpainting-based image compression. In Proceedings of computer vision winter workshop.
  3. Csurka, G., Dance, C. R., Dan, L., Willamowski, J., & Bray, C. (2004). Visual categorization with bags of keypoints. In Proceedings of ECCV workshop on statistical learning in computer vision.
  4. d’Angelo, E., Alahi, A., & Vandergheynst, P. (2012). Beyond bits: Reconstructing images from local binary descriptors. In ICPR (pp. 935–938).
  5. Dosovitskiy, A., & Brox, T. (2015). Inverting convolutional networks with convolutional networks. CoRR. arXiv:1506.02753 . · arXiv
  6. Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learninig Research, 12, 2121–2159.
  7. Erhan, D., Bengio, Y., Courville, A., & Vincent, P. (2009). Visualizing higher-layer features of a deep network. Technical report (Vol. 1341). Montreal: University of Montreal.
  8. Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style. CoRR. arXiv:1508.06576 . · arXiv
  9. Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks. In NIPS proceedings.
  10. Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. Science, 313, 5786. · DOI · Paper page
  11. Huang, W. J., & Mumford, D. (1999). Statistics of natural images and models. In Proceedings of CVPR.
  12. Jégou, H., Douze, M., Schmid, C., & Pérez, P. (2010). Aggregating local descriptors into a compact image representation. In CVPR. · DOI · Paper page
  13. Jensen, C. A., Reed, R. D., Marks, R. J., El-Sharkawi, M., Jung, J. B., Miyamoto, R., et al. (1999). Inversion of feedforward neural networks: Algorithms and applications. Proceedings of the IEEE, 87, 9. · DOI
  14. Kato, H., & Harada, T. (2014). Image reconstruction from bag-of-visual-words. In CVPR. · DOI · Paper page
  15. Krishnan, D., & Fergus, R. (2009). Fast image deconvolution using hyper-laplacian priors. In NIPS.
  16. Lee, S., & Kil, R. M. (1994). Inverse mapping of continuous functions using local and global information. IEEE Transactions on Neural Networks, 5, 3. · DOI · Paper page
  17. Linden, A., & Kindermann, J. (1989). Inversion of multilayer nets. In Proceedings of international conference on neural networks. · DOI
  18. Lu, B. L., Kita, H., & Nishikawa, Y. (1999). Inverting feedforward neural networks using linear and nonlinear programming. IEEE Transactions on Neural Networks, 10, 6. · doi:10.1109/tnn.1999.809104
  19. Nguyen, A., Yosinski, J., & Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of CVPR. · DOI · Paper page
  20. Perronnin, F., & Dance, C. (2006). Fisher kernels on visual vocabularies for image categorizaton. In CVPR.
  21. Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2014). Overfeat: Integrated recognition, localization and detection using convolutional networks. In CoRR. arXiv:1312.6229 . · arXiv
  22. Tatu, A., Lauze, F., Nielsen, M., & Kimia, B. (2011). Exploring the representation capabilities of the HOG descriptor. In ICCV workshop. · DOI
  23. Várkonyi-Kóczy, A. R., & Rövid, A. (2005). Observer based iterative neural network model inversion. In IEEE international conference on fuzzy systems. · DOI
  24. Weinzaepfel, P., Jégou, H., & Pérez, P. (2011). Reconstructing an image from its local descriptors. In CVPR. · DOI · Paper page
  25. Williams, R. J. (1986). Inverting a connectionist network mapping by back-propagation of error. In Proceedings of CogSci.
  26. Yang, J., Yu, K., & Huang, T. (2010). Supervised translation-invariant sparse coding. In CVPR. · DOI · Paper page
  27. Yosinksi, J., Clune, J., Nguyen, A., Fuchs, T., & Lipson, H. (2015). Understanding neural networks through deep visualization. In Proceedings of ICML workshop.
  28. Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In ECCV. · DOI · Paper page
  29. Zhou, X., Yu, K., Zhang, T., & Huang, T. S. (2010). Image classification using super-vector coding of local image descriptors. In ECCV. · DOI · Paper page
  30. Zhu, C., Byrd, R. H., Lu, P., & Nocedal, J. (1997). Algorithm 778: L-bfgs-b: Fortran subroutines for large-scale bound-constrained optimization. ACM Transactions on Mathematical Software (TOMS), 23(4), 550–560. · DOI · Paper page
  31. Zhu, S. C., Wu, Y., & Mumford, D. (1998). Filters, random fields and maximum entropy (FRAME): Towards a unified theory for texture modeling. IJCV, 27(2), 4.

Cited by

Metadata

Authors
Mahendran, A., & Vedaldi, A.
Venue
International Journal of Computer Vision
Publisher
Springer Science and Business Media LLC
Published
2016-05-18
Volume
120
Issue
3
Pages
233-255
ISSN
  • 0920-5691 (ISSN-L)
  • 1573-1405
DOI
10.1007/s11263-016-0911-8
OpenAlex
W2190008860
Cited by
496
References
19
FWCI
38.79
Type
journal article
Language
en
Open access
green
Licence
www.springer.com/tdm (tdm)
Funders
  • BP
  • ERC-STG (IDIU-638009)

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.