Abstract
We introduce a new visualisation technique for CNNs called Principal Feature Visualisation (PFV). It uses a single forward pass of the original network to map principal features from the final convolutional layer to the original image space as RGB channels. By working on a batch of images we can extract contrasting features, not just the most dominant ones with respect to the classification. This allows us to differentiate between several features in one image in an unsupervised manner. This enables us to assess the feasibility of transfer learning and to debug a pre-trained classifier by localising misleading or missing features.
Funded by The Norwegian Research Council, grant no. 259869.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: Advances in Neural Information Processing Systems, vol. 2018-Decem, pp. 9505–9515. Neural Information Processing Systems Foundation, October 2018. http://arxiv.org/abs/1810.03292
Agarwal, C., Schonfeld, D., Nguyen, A.: Removing input features via a generative model to explain their attributions to an image classifier’s decisions (2019). http://arxiv.org/abs/1910.04256
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), 1–46 (2015). https://doi.org/10.1371/journal.pone.0130140
Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. CVPR 2016(1), M1–M6 (2016). https://doi.org/10.5465/ambpp.2004.13862426
Ghorbani, A., Wexler, J., Zou, J., Kim, B.: Towards automatic concept-based explanations. NeurIPS, February 2019. https://github.com/amiratag/ACE, http://arxiv.org/abs/1902.03129
Kim, B., et al.: Interpretability beyond feature attribution: quantitative Testing with Concept Activation Vectors (TCAV). In: 35th International Conference on Machine Learning, ICML 2018, vol. 6, pp. 4186–4195 (2018)
Lapuschkin, S., Wäldchen, S., Binder, A., Montavon, G., Samek, W., Müller, K.R.: Unmasking Clever Hans predictors and assessing what machines really learn. Nat. Commun. 10(1), 1–8 (2019). https://doi.org/10.1038/s41467-019-08987-4
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should i trust you?” Explaining the predictions of any classifier. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 13–17, pp. 1135–1144 (2016). https://doi.org/10.1145/2939672.2939778
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128(2), 336–359 (2020). https://doi.org/10.1007/s11263-019-01228-7, http://gradcam.cloudcv.org
Shinya, Y., Simo-Serra, E., Suzuki, T.: Understanding the effects of pre-training for object detectors via eigenspectrum. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, October 2019
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 3145–3153. PMLR, International Convention Centre, Sydney, Australia, August 06–11, 2017. http://proceedings.mlr.press/v70/shrikumar17a.html
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: 2nd International Conference on Learning Representations, ICLR 2014 - Workshop Track Proceedings, pp. 1–8 (2014)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1 (2014). https://doi.org/10.1016/j.infsof.2008.09.005, http://arxiv.org/abs/1409.1556
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. In: 3rd International Conference on Learning Representations, ICLR 2015 - Workshop Track Proceedings (2015)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhang, J., Bargal, S.A., Lin, Z., Brandt, J., Shen, X., Sclaroff, S.: Top-down neural attention by excitation backprop. Int. J. Comput. Vis. 126(10), 1084–1102 (2018). https://doi.org/10.1007/s11263-017-1059-x, http://arxiv.org/abs/1608.00507
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Bakken, M., Kvam, J., Stepanov, A.A., Berge, A. (2020). Principal Feature Visualisation in Convolutional Neural Networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12368. Springer, Cham. https://doi.org/10.1007/978-3-030-58592-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-58592-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58591-4
Online ISBN: 978-3-030-58592-1
eBook Packages: Computer ScienceComputer Science (R0)