Abstract
Classification accuracy for case-based classifiers depends critically on the features used for case retrieval. Feature extraction from deep learning classifier models has proven a useful method for generating case-based classifier features, especially for domains in which manual feature engineering is costly or difficult. Previous work has explored how the quality of extracted features is influenced by structural choices such as the number of features extracted and the location/depth of extraction. This paper investigates how feature quality is influenced by another factor: the choice of the network model itself. We consider a selection of deep learning models for a computer vision classification task and test the accuracy of a case-based classifier using features extracted from them, both as the sole feature source and in combination with a supplementary set of knowledge-engineered features. Results suggest that feature quality reflects a trade-off between model complexity and training data requirements and provide lessons for the selection of deep learning architectures for feature extraction to support case-based classification.
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
References
Aamodt, A., Plaza, E.: Case-based reasoning: foundational issues, methodological variations, and system approaches. AI Commun. 7(1), 39–52 (1994)
Barletta, R., Mark, W.: Explanation-based indexing of cases. In: Kolodner, J. (ed.) Proceedings of a Workshop on Case-Based Reasoning, pp. 50–60. DARPA, Morgan Kaufmann, Palo Alto (1988)
Barnett, A.J., et al.: Interpretable mammographic image classification using case-based reasoning and deep learning. In: IJCAI Workshops 2021 (2021)
Bhatta, S., Goel, A.: Model-based learning of structural indices to design cases. In: Proceedings of the IJCAI-93 Workshop on Reuse of Design, pp. A1–A13. IJCAI, Chambery (1993)
Bonzano, A., Cunningham, P., Smyth, B.: Using introspective learning to improve retrieval in CBR: a case study in air traffic control. In: Leake, D.B., Plaza, E. (eds.) ICCBR 1997. LNCS, vol. 1266, pp. 291–302. Springer, Heidelberg (1997). https://doi.org/10.1007/3-540-63233-6_500
Chai, J., Zeng, H., Li, A., Ngai, E.W.: Deep learning in computer vision: a critical review of emerging techniques and application scenarios. Mach. Learn. Appl. 6, 100134 (2021)
Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8930–8941. Curran (2019)
Cox, M., Ram, A.: Introspective multistrategy learning: on the construction of learning strategies. Artif. Intell. 112(1–2), 1–55 (1999)
Domeshek, E.: Indexing stories as social advice. In: Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 16–21. AAAI Press, Menlo Park (1991)
Fox, S., Leake, D.: Introspective reasoning for index refinement in case-based reasoning. J. Exp. Theor. Artif. Intell. 13(1), 63–88 (2001)
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)
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks (2016). arXiv:1608.06993
Kenny, E.M., Keane, M.T.: Twin-systems to explain artificial neural networks using case-based reasoning: comparative tests of feature-weighting methods in ANN-CBR twins for XAI. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (2019)
Khan, A., Sohail, A., Zahoora, U., Qureshi, A.S.: A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53, 5455–5516 (2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, vol. 1, pp. 1097–1105 (2012)
Leake, D.: An indexing vocabulary for case-based explanation. In: Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 10–15. AAAI Press, Menlo Park (1991)
Leake, D.: CBR in context: the present and future. In: Leake, D. (ed.) Case-Based Reasoning: Experiences, Lessons, and Future Directions, pp. 3–30. AAAI Press, Menlo Park (1996). http://www.cs.indiana.edu/~leake/papers/a-96-01.html
Leake, D., Wilkerson, Z., Crandall, D.: Extracting case indices from convolutional neural networks: a comparative study. In: Keane, M.T., Wiratunga, N. (eds.) ICCBR 2022. LNCS, vol. 13405, pp. 81–95. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-14923-8_6
Leake, D., Ye, X.: Harmonizing case retrieval and adaptation with alternating optimization. In: Sánchez-Ruiz, A.A., Floyd, M.W. (eds.) ICCBR 2021. LNCS (LNAI), vol. 12877, pp. 125–139. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86957-1_9
Li, O., Liu, H., Chen, C., Rudin, C.: Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (2017)
Liao, C., Liu, A., Chao, Y.: A machine learning approach to case adaptation. In: 2018 IEEE First International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), pp. 106–109 (2018)
Main, J., Dillon, T.S.: A hybrid case-based reasoner for footwear design. In: Althoff, K.-D., Bergmann, R., Branting, L.K. (eds.) ICCBR 1999. LNCS, vol. 1650, pp. 497–509. Springer, Heidelberg (1999). https://doi.org/10.1007/3-540-48508-2_36
Mathisen, B.M., Aamodt, A., Bach, K., Langseth, H.: Learning similarity measures from data. Progr. Artif. Intell. 9, 129–143 (2019)
Richter, M.: Introduction. In: Lenz, M., Bartsch-Spörl, B., Burkhard, H.D., Wess, S. (eds.) CBR Technology: From Foundations to Applications, chap. 1, pp. 1–15. Springer, Berlin (1998)
Rudin, C.: Please stop explaining black box models for high stakes decisions. Nature Mach. Intell. 1, 206–215 (2019)
Sani, S., Wiratunga, N., Massie, S.: Learning deep features for kNN-based human activity recognition. In: Proceedings of ICCBR 2017 Workshops (CAW, CBRDL, PO-CBR), Doctoral Consortium, and Competitions co-located with the 25th International Conference on Case-Based Reasoning (ICCBR 2017), Trondheim, Norway, 26–28 June 2017. CEUR Workshop Proceedings, vol. 2028, pp. 95–103. CEUR-WS.org (2017)
Schank, R., et al.: Towards a general content theory of indices. In: Proceedings of the 1990 AAAI Spring Symposium on Case-Based Reasoning. AAAI Press, Menlo Park (1990)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). https://doi.org/10.48550/ARXIV.1409.1556, arXiv:1409.1556
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision (2015). arXiv:1512.00567
Turner, J.T., Floyd, M.W., Gupta, K.M., Aha, D.W.: Novel object discovery using case-based reasoning and convolutional neural networks. In: Cox, M.T., Funk, P., Begum, S. (eds.) ICCBR 2018. LNCS (LNAI), vol. 11156, pp. 399–414. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01081-2_27
Turner, J.T., Floyd, M.W., Gupta, K., Oates, T.: NOD-CC: a hybrid CBR-CNN architecture for novel object discovery. In: Bach, K., Marling, C. (eds.) ICCBR 2019. LNCS (LNAI), vol. 11680, pp. 373–387. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29249-2_25
Wilkerson, Z., Leake, D., Crandall, D.J.: On combining knowledge-engineered and network-extracted features for retrieval. In: Sánchez-Ruiz, A.A., Floyd, M.W. (eds.) ICCBR 2021. LNCS (LNAI), vol. 12877, pp. 248–262. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86957-1_17
Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning - a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI) 40(8), 1–14 (2018)
Ye, X., Leake, D., Crandall, D.: Case adaptation with neural networks: capabilities and limitations. In: Keane, M.T., Wiratunga, N. (eds.) ICCBR 2022. LNCS, vol. 13405, pp. 143–158. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-14923-8_10
Acknowledgments
This work was funded by the US Department of Defense (Contract W52P1J2093009), and by the Department of the Navy, Office of Naval Research (Award N00014-19-1-2655).
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
Leake, D., Wilkerson, Z., Vats, V., Acharya, K., Crandall, D. (2023). Examining the Impact of Network Architecture on Extracted Feature Quality for CBR. In: Massie, S., Chakraborti, S. (eds) Case-Based Reasoning Research and Development. ICCBR 2023. Lecture Notes in Computer Science(), vol 14141. Springer, Cham. https://doi.org/10.1007/978-3-031-40177-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-40177-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40176-3
Online ISBN: 978-3-031-40177-0
eBook Packages: Computer ScienceComputer Science (R0)