Abstract
The most popular methods for Artificial Intelligence such as Deep Neural Networks are, for the vast majority, considered black boxes. It is necessary to explain their decisions to understand the input data which influence most the result.
Methods presented in this paper aim at an explanation in image classification tasks: which data in the input are the most important for the result. We further extend the Feature Explanation Method (FEM) from our previous work, transforming it into a multi-layered FEM (MLFEM). The evaluation of the method is designed by comparison of explanation maps with human Gaze Fixation Density maps (GFDM). We show that proposed MLFEM outperforms FEM and popular DNN explanation methods in terms of classical comparison metrics with GFDM.
Supported by LaBRI.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ayyar, M.P., Benois-Pineau, J., Zemmari, A.: White box methods for explanations of convolutional neural networks in image classification tasks (2021)
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you? explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Proceedings of European Conference on Computer Vision, pp. 818–833. Springer, Cham (2014). https://doi.org/10.48550/arXiv.1311.2901
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 (2019)
Smilkov, D., Thorat, N., Kim, B., Viégas, F.B., Wattenberg, M.: Smoothgrad: removing noise by adding noise. CoRR, abs/1706.03825:1–10 (2017)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of International Conference on Machine Learning, PMLR, pp. 3319–3328 (2017)
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, e0130140 (2015)
Ahmed Asif Fuad, K., Martin, P.E., Giot, R., Bourqui, R., Benois-Pineau, J., Zemmari, A.: Features understanding in 3D CNNs for actions recognition in video. In: Tenth International Conference on Image Processing Theory, Tools and Applications, IPTA 2020, Paris, France, October 2020
Zemmari, A., Benois-Pineau, J.: Introducing Domain Knowledge. In: Deep Learning in Mining of Visual Content. SCS, pp. 87–97. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-34376-7_9
Obeso, A.M., Benois-Pineau, J., García-Vázquez, M.S., Ramírez-Acosta, A.A.: Visual vs internal attention mechanisms in deep neural networks for image classification and object detection. Pattern Recognit. 123, 108411 (2022)
Rousseau, F., Drumetz, L., Fablet, R.: Residual networks as flows of diffeomorphisms. J. Math. Imag. Vis. 62, 04 (2020)
Kingma, D.P., Lei Ba, J.: A method for stochastic optimization, Adam (2017)
Jouis, G., Mouchère, H., Picarougne, F., Hardouin, A.: Anchors vs attention: Comparing XAI on a real-life use case. In: ICPR Workshops (3). LNCS, vol. 12663, pp. 219–227. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-68796-0_16
Jiang, M., Huang, S., Duan, J., Zhao, Q.: Salicon: Saliency in context. In: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, vol. 6 (2015)
Borji, A., Itti, L.: CAT2000: a large scale fixation dataset for boosting saliency research. CoRR, abs/1505.03581 (2015)
Le Meur, O., Baccino, T.: Methods for comparing scanpaths and saliency maps: strengths and weaknesses. Behav. Res. Methods 45(1), 251–266 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Bourroux, L., Benois-Pineau, J., Bourqui, R., Giot, R. (2022). Multi Layered Feature Explanation Method for Convolutional Neural Networks. In: El Yacoubi, M., Granger, E., Yuen, P.C., Pal, U., Vincent, N. (eds) Pattern Recognition and Artificial Intelligence. ICPRAI 2022. Lecture Notes in Computer Science, vol 13363. Springer, Cham. https://doi.org/10.1007/978-3-031-09037-0_49
Download citation
DOI: https://doi.org/10.1007/978-3-031-09037-0_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09036-3
Online ISBN: 978-3-031-09037-0
eBook Packages: Computer ScienceComputer Science (R0)