Adaptive explainable artificial intelligence for visual defect inspection.
Abstract
Explainable Artificial Intelligence promises to deliver means so that humans better understand the rationale behind a particular machine learning model. In the image domain, such information is frequently conveyed through heat maps. Along the same line, information regarding defect detection for unsupervised methods applied to images can be conveyed through anomaly maps. Nevertheless, heat maps or anomaly maps can convey inaccurate information (artifacts), or their perceptions may differ across different persons. Therefore, the user experience could be enhanced by collecting human feedback and creating predictive models on how these could be recolored to bridge the gap between the original heat maps and anomaly maps created with explainability techniques and the output expected by humans. We envision this work as relevant in at least two scenarios. First, enhance anomaly and heat maps when conveying information regarding machine vision models deployed in production to remove information deemed unnecessary by the user but systematically present through the explainability technique due to underlying model issues (artifacts). Second, adapt anomaly and heat maps based on users’ perceptual needs and preferences.
References
[1]
K.S. Aggour, V.K. Gupta, D. Ruscitto, L. Ajdelsztajn, X. Bian, K.H. Brosnan, N.C. Kumar, V. Dheeradhada, T. Hanlon, N. Iyer, et al., Artificial intelligence/machine learning in manufacturing and inspection: A ge perspective, MRS Bulletin 44 (2019) 545–558.
[2]
A.B. Arrieta, N. Díaz-Rodríguez, J. Del Ser, A. Bennetot, S. Tabik, A. Barbado, S. García, S. Gil-López, D. Molina, R. Benjamins, et al., Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai, Information fusion 58 (2020) 82–115.
[3]
V. Buhrmester, D. Münch, M. Arens, Analysis of explainers of black box deep neural networks for computer vision: A survey, Machine Learning and Knowledge Extraction 3 (2021) 966–989.
[4]
R.J. Campello, D. Moulavi, J. Sander, Density-based clustering based on hierarchical density estimates, in: Advances in Knowledge Discovery and Data Mining: 17th Pacific-Asia Conference, PAKDD 2013, 17, Springer, Gold Coast, Australia, 2013, pp. 160–172. April 14-17, 2013, Proceedings, Part II.
[5]
T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785–794.
[6]
R.T. Chin, C.A. Harlow, Automated visual inspection: A survey, IEEE transactions on pattern analysis and machine intelligence 4 (1982) 557–573.
[7]
D.C. Ciresan, U. Meier, J. Masci, L.M. Gambardella, J. Schmidhuber, Flexible, high performance convolutional neural networks for image classification, in: Twenty-second international joint conference on artificial intelligence, Citeseer, 2011.
[8]
T. Czimmermann, G. Ciuti, M. Milazzo, M. Chiurazzi, S. Roccella, C.M. Oddo, P. Dario, Visual-based defect detection and classification approaches for industrial applications—a survey, Sensors 20 (2020) 1459.
[9]
F. Doshi-Velez, B. Kim, Towards a rigorous science of interpretable machine learning, arXiv preprint (2017) arXiv:1702.08608.
[10]
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
[11]
J. Hua, Z. Xiong, J. Lowey, E. Suh, E.R. Dougherty, Optimal number of features as a function of sample size for various classification rules, Bioinformatics 21 (2005) 1509–1515.
[12]
A. Hudon, T. Demazure, A. Karran, P.M. Léger, S. Sénécal, Explainable artificial intelligence (xai): how the visualization of ai predictions affects user cognitive load and confdence, Information Systems and Neuroscience: NeuroIS Retreat 2021, Springer, 2021, pp. 237–246.
[13]
F. Hussain, R. Hussain, E. Hossain, Explainable artificial intelligence (xai): An engineering perspective, arXiv preprint (2021) arXiv:2101.03613.
[14]
S.R. Islam, W. Eberle, S.K. Ghafoor, M. Ahmed, Explainable artificial intelligence approaches: A survey, arXiv preprint (2021) arXiv:2101.09429.
[15]
A. Kraskov, H. Stögbauer, P. Grassberger, Erratum: estimating mutual information, [phys. rev. e 69, 066138 (2004)] Physical Review E 83 (2011).
[16]
S. Li, D. Chen, Y. Chen, L. Yuan, L. Zhang, Q. Chu, B. Liu, N. Yu, Improve unsupervised pretraining for few-label transfer, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10201–10210.
[17]
R. Netzorg, J. Li, B. Yu, Improving prototypical part networks with reward reweighing, reselection, and retraining, arXiv preprint (2023) arXiv:2307.03887.
[18]
A.F. Norcio, J. Stanley, Adaptive human-computer interfaces: A literature survey and perspective, IEEE Transactions on Systems, Man, and cybernetics 19 (1989) 399–408.
[19]
A. Rawal, J. McCoy, D.B. Rawat, B.M. Sadler, R.S. Amant, Recent advances in trustworthy explainable artificial intelligence: Status, challenges, and perspectives, IEEE Transactions on Artificial Intelligence 3 (2021) 852–866.
[20]
M.T. Ribeiro, S. Singh, C. Guestrin, 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, 2016, pp. 1135–1144.
[21]
J.M. Rožanec, P. Zajec, J. Keizer, E. Trajkova, B. Fortuna, B. Brecelj, B. Šircelj, D. Mladenić, Enhancing manual revision in manufacturing with ai-based defect hints, in: Central European Conference on Information and Intelligent Systems, Faculty of Organization and Informatics Varazdin, 2022, pp. 357–363.
[22]
Rožanec, J.M., Zajec, P., Theodoropoulos, S., Koehorst, E., Fortuna, B., Mladenić, D., 2022b. Robust anomaly map assisted multiple defect detection with supervised classification techniques. arXiv preprint arXiv:2212.09352.
[23]
J.M. Rožanec, P. Zajec, S. Theodoropoulos, E. Koehorst, B. Fortuna, D. Mladenić, Synthetic data augmentation using gan for improved automated visual inspection, arXiv preprint (2022) arXiv:2212.09317.
[24]
J.E. See, Visual inspection: a review of the literature, Sandia National Laboratories, Albuquerque, New Mexico, 2012, Sandia Report SAND2012-8590.
[25]
R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE international conference on computer vision, 2017, pp. 618–626.
[26]
X. Wu, L. Xiao, Y. Sun, J. Zhang, T. Ma, L. He, A survey of human-in-the-loop for machine learning, Future Generation Computer Systems (2022).
[27]
V. Zavrtanik, M. Kristan, D. Skočaj, Draem-a discriminatively trained reconstruction embedding for surface anomaly detection, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 8330–8339.
[28]
X. Zeng, T.R. Martinez, Distribution-balanced stratified cross-validation for accuracy estimation, Journal of Experimental & Theoretical Artificial Intelligence 12 (2000) 1–12.
Recommendations
Explainable artificial intelligence, lawyer's perspective
ICAIL '21: Proceedings of the Eighteenth International Conference on Artificial Intelligence and LawExplainable artificial intelligence (XAI) is a research direction that was already put under scrutiny, in particular in the AI&Law community. Whilst there were notable developments in the area of (general, not necessarily legal) XAI, user experience ...
Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence
AbstractArtificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to ...
Highlights- A novel four-axis framework to examine a model for robustness and explainability.
- Formulation of research questions at each axis and its corresponding taxonomy.
- Discussion of different explainability assessment methods.
- A novel ...
Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction
AbstractArtificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © 2024.
Publisher
Elsevier Science Publishers B. V.
Netherlands
Publication History
Published: 01 January 2024
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 01 Feb 2025