Abstract
This paper introduces an evaluation procedure to validate the efficacy of explanation methods for Convolutional Neural Network (CNN) models in ordinal regression tasks. Two ordinal methods are contrasted against a baseline using cross-entropy, across four datasets. A statistical analysis demonstrates that attribution methods, such as Grad-CAM and IBA, perform significantly better when used with ordinal regression CNN models compared to a baseline approach in most ordinal and nominal metrics. The study suggests that incorporating ordinal information into the attribution map construction process may improve the explanations further.
This work has been partially subsidised by “Agencia Española de Investigación” (Spain) (grant ref.: PID2020-115454GB-C22/AEI/10.13039/501100011033). Javier Barbero-Gómez’s research has been subsidised by the FPI Predoctoral Program of the Spanish Ministry of Science, Innovation and Universities (MCIU) [grant reference PRE2018-085659].
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
Notes
- 1.
Note that the area contribution can be negative for those cases where the performance of the LeRF curve is higher than that of the MoRF curve.
- 2.
References
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), e0130140 (2015). https://doi.org/10.1371/journal.pone.0130140
Barbero-Gómez, J., Gutiérrez, P.A., Hervás-Martínez, C.: Error-correcting output codes in the framework of deep ordinal classification. Neural Process. Lett. (2022). https://doi.org/10.1007/s11063-022-10824-7
Chattopadhyay, A., Sarkar, A., Howlader, P., Balasubramanian, V.N.: Grad-CAM++: improved visual explanations for deep convolutional networks. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 839–847 (2018). https://doi.org/10.1109/WACV.2018.00097
Cruz-Ramírez, M., Hervás-Martínez, C., Sánchez-Monedero, J., Gutiérrez, P.A.: Metrics to guide a multi-objective evolutionary algorithm for ordinal classification. Neurocomputing 135, 21–31 (2014)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255, June 2009. https://doi.org/10.1109/CVPR.2009.5206848
Eidinger, E., Enbar, R., Hassner, T.: Age and gender estimation of unfiltered faces. IEEE Trans. Inf. Forensics Secur. 9(12), 2170–2179 (2014). https://doi.org/10.1109/TIFS.2014.2359646
Fu, R., Hu, Q., Dong, X., Guo, Y., Gao, Y., Li, B.: Axiom-based Grad-CAM: towards accurate visualization and explanation of CNNs. Technical report. arXiv:2008.02312, arXiv, August 2020
Gutiérrez, P.A., Pérez-Ortiz, M., Sánchez-Monedero, J., Fernández-Navarro, F., Hervás-Martínez, C.: Ordinal regression methods: survey and experimental study. IEEE Trans. Knowl. Data Eng. 28(1), 127–146 (2016). https://doi.org/10.1109/TKDE.2015.2457911
Jantzen, J., Norup, J., Dounias, G., Bjerregaard, B.: Pap-smear benchmark data for pattern classification. In: Nature Inspired Smart Information Systems (NiSIS), January 2005
Khakzar, A., Khorsandi, P., Nobahari, R., Navab, N.: Do explanations explain? Model knows best. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10234–10243. IEEE, New Orleans, LA, USA, June 2022. https://doi.org/10.1109/CVPR52688.2022.01000
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 [cs], January 2017
Lee, R.S., Gimenez, F., Hoogi, A., Miyake, K.K., Gorovoy, M., Rubin, D.L.: A curated mammography data set for use in computer-aided detection and diagnosis research. Sci. Data 4(1), 170177 (2017). https://doi.org/10.1038/sdata.2017.177
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., Müller, K.R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn. 65, 211–222 (2017). https://doi.org/10.1016/j.patcog.2016.11.008
Nayar, R., Wilbur, D.C.: The Bethesda System for Reporting Cervical Cytology: Definitions, Criteria, and Explanatory Notes. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-11074-5
Pinto da Costa, J.F., Alonso, H., Cardoso, J.S.: The unimodal model for the classification of ordinal data. Neural Netw. 21(1), 78–91 (2008). https://doi.org/10.1016/j.neunet.2007.10.003
Schulz, K., Sixt, L., Tombari, F., Landgraf, T.: Restricting the Flow: Information Bottlenecks for Attribution, May 2020
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. Vision 128(2), 336–359 (2019). https://doi.org/10.1007/s11263-019-01228-7
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, April 2014
Smirnov, N.: Table for estimating the goodness of fit of empirical distributions. Ann. Math. Stat. 19(2), 279–281 (1948). https://doi.org/10.1214/aoms/1177730256
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. Technical report. arXiv:1412.6806, arXiv, April 2015
Wilcoxon, F.: Individual comparisons by ranking methods. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics: Methodology and Distribution. Springer Series in Statistics, pp. 196–202. Springer, New York (1992). https://doi.org/10.1007/978-1-4612-4380-9_16
Zeiler, M.D., Fergus, R.: Visualizing and Understanding Convolutional Networks, Novomber 2013. https://doi.org/10.48550/arXiv.1311.2901
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. Technical report. arXiv:1512.04150, arXiv, December 2015
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Barbero-Gómez, J., Cruz, R., Cardoso, J.S., Gutiérrez, P.A., Hervás-Martínez, C. (2023). Evaluating the Performance of Explanation Methods on Ordinal Regression CNN Models. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14135. Springer, Cham. https://doi.org/10.1007/978-3-031-43078-7_43
Download citation
DOI: https://doi.org/10.1007/978-3-031-43078-7_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43077-0
Online ISBN: 978-3-031-43078-7
eBook Packages: Computer ScienceComputer Science (R0)