Abstract
Deep Learning models have recently achieved incredible performances in the Computer Vision field and are being deployed in an ever-growing range of real-life scenarios. Since they do not intrinsically provide insights of their inner decision processes, the field of eXplainable Artificial Intelligence emerged. Different XAI techniques have already been proposed, but the existing literature lacks methods to quantitatively compare different explanations, and in particular the semantic component is systematically overlooked. In this paper we introduce quantitative and ontology-based techniques and metrics in order to enrich and compare different explanations and XAI algorithms.
A. Perotti—Acknowledges support from Intesa Sanpaolo Innovation Center. The funder had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
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
Notes
References
Binder, A., Bach, S., Montavon, G., et al.: Layer-wise relevance propagation for deep neural network architecture. In: ICISA 2016 (2016)
Chakraborty, S., Tomsett, R., Raghavendra, R., et al.: Interpretability of deep learning models: a survey of results (2017). https://doi.org/10.1109/UIC-ATC.2017.8397411
Chollet, F.: Deep Learning with Python. Manning Publishers & Co (2018)
Deng, J., Dong, W., Socher, R., et al.: ImageNet: a large-scale hierarchical image database (2009). https://doi.org/10.1109/CVPR.2009.5206848
Erhan, D., Bengio, Y., Courville, A., Vincent, P.: Visualizing Higher-Layer Features of a Deep Network (2009). arXiv:1903.02313
Esteva, A., Robicquet, A., Ramsundar, B., et al.: A guide to deep learning in healthcare (2019). https://doi.org/10.1038/s41591-018-0316-z
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. O’Reilly Media (2018)
Goodman, B., Flaxman, S.: European Union regulations on algorithmic decision-making and a “right to explanation” (2017). https://doi.org/10.1609/aimag.v38i3.2741
Guidotti, R., Monreale, A., Ruggieri, S., et al.: A Survey of Methods for Explaining Black Box Models (2018). arXiv:1802.01933v3
Haykin, S.: Neural Networks and Learning Machines. Pearson Prentice Hall (2009). ISBN: 978-0-13-147139-9
Li, H., Cai, J., Nguyen, T., Zheng, J.: A benchmark for semantic image segmentation. In: ICME (2013)
Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Petsiuk, V., Das, A., Saenko, K.: RISE: Randomized Input Sampling for Explanation of Black-Box Models (2018). arXiv:1806.07421v3
Rao, Q., Frtunikj, J.: Deep Learning for Self-driving Cars: Chances and Challenges (2018). https://doi.org/10.1145/3194085.3194087
Ribeiro, M.T., Singh, S., Guestrin, C.: Why Should I Trust You? Explaining the Predictions of Any Classifier (2016). arXiv:1602.04938v3
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall Press (1994). ISBN 0136042597 9780136042594
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R.: Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization (2017). arXiv:1610.02391v3
Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for Simplicity: The All Convolutional Net (2015). arXiv:1412.6806v3
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J.: Rethinking the Inception Architecture for Computer Vision (2015). arXiv:1512.00567v3
Wu, Z., Palmer, M.: Verbs Semantics and Lexical Selection (2004). https://doi.org/10.3115/981732.981751
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ghidini, V., Perotti, A., Schifanella, R. (2019). Quantitative and Ontology-Based Comparison of Explanations for Image Classification. In: Nicosia, G., Pardalos, P., Umeton, R., Giuffrida, G., Sciacca, V. (eds) Machine Learning, Optimization, and Data Science. LOD 2019. Lecture Notes in Computer Science(), vol 11943. Springer, Cham. https://doi.org/10.1007/978-3-030-37599-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-37599-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37598-0
Online ISBN: 978-3-030-37599-7
eBook Packages: Computer ScienceComputer Science (R0)