Abstract
Convolutional Neural Networks (CNNs) are nowadays the model of choice in Computer Vision, thanks to their ability to automatize the feature extraction process in visual tasks. However, the knowledge acquired during training is fully sub-symbolic, and hence difficult to understand and explain to end users. In this paper, we propose a new technique called HOLMES (HOLonym-MEronym based Semantic inspection) that decomposes a label into a set of related concepts, and provides component-level explanations for an image classification model. Specifically, HOLMES leverages ontologies, web scraping and transfer learning to automatically construct meronym (parts)-based detectors for a given holonym (class). Then, it produces heatmaps at the meronym level and finally, by probing the holonym CNN with occluded images, it highlights the importance of each part on the classification output. Compared to state-of-the-art saliency methods, HOLMES takes a step further and provides information about both where and what the holonym CNN is looking at. It achieves so without relying on densely annotated datasets and without forcing concepts to be associated to single computational units. Extensive experimental evaluation on different categories of objects (animals, tools and vehicles) shows the feasibility of our approach. On average, HOLMES explanations include at least two meronyms, and the ablation of a single meronym roughly halves the holonym model confidence. The resulting heatmaps were quantitatively evaluated using the deletion/insertion/preservation curves. All metrics were comparable to those achieved by GradCAM, while offering the advantage of further decomposing the heatmap in human-understandable concepts. In addition, results were largely above chance level, thus highlighting both the relevance of meronyms to object classification, as well as HOLMES ability to capture it. The code is available at https://github.com/FrancesC0de/HOLMES.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)
Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: quantifying interpretability of deep visual representations. In: Computer Vision and Pattern Recognition (2017)
Bau, D., Zhu, J.Y., Strobelt, H., Lapedriza, A., Zhou, B., Torralba, A.: Understanding the role of individual units in a deep neural network. Proc. Natl. Acad. Sci. 117(48), 30071–30078 (2020)
Chen, C., Li, O., Barnett, A., Su, J., Rudin, C.: This looks like that: deep learning for interpretable image recognition. Adv. Neural Inf. Process. Syst. 32, 8930–8941 (2019)
Chen, X., Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., Yuille, A.L.: Detect what you can: detecting and representing objects using holistic models and body parts. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1979–1986 (2014)
Confalonieri, R., et al.: An ontology-based approach to explaining artificial neural networks. CoRR abs/1906.08362 (2019)
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 (2009)
Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665–673 (2020)
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: International Conference on Learning Representations (2019)
Ghidini, V., Perotti, A., Schifanella, R.: Quantitative and ontology-based comparison of explanations for image classification. In: Nicosia, G., Pardalos, P., Umeton, R., Giuffrida, G., Sciacca, V. (eds.) LOD 2019. LNCS, vol. 11943, pp. 58–70. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-37599-7_6
Gonzalez-Garcia, A., Modolo, D., Ferrari, V.: Do semantic parts emerge in convolutional neural networks? Int. J. Comput. Vis. 126, 476–494 (2018)
Goodman, B., Flaxman, S.: European Union regulations on algorithmic decision making and a “Right to Explanation’’. AI Mag. 38, 50–57 (2016)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 1–42 (2018)
Jiang, H., Kim, B., Guan, M., Gupta, M.: To trust or not to trust a classifier. Adv. Neural Inf. Process. Syst. 31, 5541–5552 (2018)
Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., et al.: Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). In: International Conference on Machine Learning, pp. 2668–2677. PMLR (2018)
Lim, D., Lee, H., Kim, S.: Building reliable explanations of unreliable neural networks: locally smoothing perspective of model interpretation. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6464–6473 (2021)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 4765–4774 (2017)
Massouh, N., Babiloni, F., Tommasi, T., Young, J., Hawes, N., Caputo, B.: Learning deep visual object models from noisy web data: how to make it work. In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5564–5571 (2017)
Miller, G.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Molinari, D., Pasquale, G., Natale, L., Caputo, B.: Automatic creation of large scale object databases from web resources: a case study in robot vision. In: International Conference on Image Analysis and Processing (2019)
Morra, L., Lamberti, F.: Benchmarking unsupervised near-duplicate image detection. Expert Syst. Appl. 135, 313–326 (2019)
Obermeyer, Z., Powers, B., Vogeli, C., Mullainathan, S.: Dissecting racial bias in an algorithm used to manage the health of populations. Science 366(6464), 447–453 (2019)
Petsiuk, V., Das, A., Saenko, K.: Rise: randomized input sampling for explanation of black-box models. In: British Machine Vision Conference (2018)
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)
Rodríguez, N.D., et al.: Explainable neural-symbolic learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case. Inf. Fusion 79, 58–83 (2022)
Samanta, P., Jain, S.: Analysis of perceptual hashing algorithms in image manipulation detection. Procedia Comput. Sci. 185, 203–212 (2021). https://doi.org/10.1016/j.procs.2021.05.021
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., Müller, K.R.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst. 28(11), 2660–2673 (2017)
Sarraf, A., Azhdari, M., Sarraf, S.: A comprehensive review of deep learning architectures for computer vision applications. Am. Sci. Res. J. Eng. Technol. Sci. 77, 1–29 (2021)
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)
Shyu, M.L., Chen, S.C., Sarinnapakorn, K., Chang, L.: A novel anomaly detection scheme based on principal component classifier. In: Proceedings of International Conference on Data Mining, January 2003
Siblini, W., Fréry, J., He-Guelton, L., Oblé, F., Wang, Y.-Q.: Master your metrics with calibration. In: Berthold, M.R., Feelders, A., Krempl, G. (eds.) IDA 2020. LNCS, vol. 12080, pp. 457–469. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-44584-3_36
Silberer, C., Ferrari, V., Lapata, M.: Visually grounded meaning representations. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2284–2297 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)
Steging, C., Schomaker, L., Verheij, B.: The XAI paradox: systems that perform well for the wrong reasons. In: Proceedings of the 31st Benelux Conference on A.I. and the 28th Belgian Dutch Conference on Machine Learning (2019)
Yao, Y., et al.: Exploiting web images for multi-output classification: from category to subcategories. IEEE Trans. Neural Netw. Learn. Syst. 31(7), 2348–2360 (2020)
Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? Adv. Neural Inf. Process. Syst. 27, 3320–3328 (2014)
Zhang, C., Wang, Q., Xie, G., Wu, Q., Shen, F., Tang, Z.: Robust learning from noisy web images via data purification for fine-grained recognition. IEEE Trans. Multimed. 24, 1198–1209 (2021)
Zhang, Q., Wu, Y.N., Zhu, S.C.: Interpretable convolutional neural networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8827–8836 (2018)
Zhou, B., Khosla, A., Lapedriza, À., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. In: International Conference on Learning Representations abs/1412.6856 (2015)
Zhou, B., Sun, Y., Bau, D., Torralba, A.: Interpretable basis decomposition for visual explanation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 122–138. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_8
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
Dibitonto, F., Garcea, F., Panisson, A., Perotti, A., Morra, L. (2023). HOLMES: HOLonym-MEronym Based Semantic Inspection for Convolutional Image Classifiers. In: Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1902. Springer, Cham. https://doi.org/10.1007/978-3-031-44067-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-44067-0_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44066-3
Online ISBN: 978-3-031-44067-0
eBook Packages: Computer ScienceComputer Science (R0)