Interpretability to Enhance Transparency in Computer Vision System

References

[1] A. Taeihagh, “Governance of Artificial Intelligence,” Policy and Society, vol. 40, no. 2, pp. 137–157, 2021. doi:10.1080/14494035.2021.1928377

[2] C. Burr and D. Leslie, “Ethical assurance: A practical approach to the responsible design, development, and deployment of data-Driven Technologies,” AI and Ethics, vol. 3, no. 1, pp. 73–98, 2022. doi:10.1007/s43681-022-00178-0

[3] Y. Chen, E. W. Clayton, L. L. Novak, S. Anders, and B. Malin, “Human-centered design to address biases in artificial intelligence,” Journal of Medical Internet Research, vol. 25, 2023. doi:10.2196/43251

[4] European Commission, "White Paper on Artificial Intelligence: a European approach to excellence and trust," 2020. [Online]. Available: https://commission.europa.eu/publications/white-paper-artificial-intelligence-european-approach-excellence-and-trust_en. [Accessed: 18 January 2023].

[5] J. A. Kroll, “Outlining traceability,” Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, 2021. doi:10.1145/3442188.3445937

[6] A. Meijer, "Understanding the Complex Dynamics of Transparency," Public Administration Review, vol. 73, no. 3, pp. 429-439, 2013.

[7] S. Douglas and A. Meijer, "Transparency and public value—analyzing the transparency practices and value creation of public utilities," International Journal of Public Administration, vol. 39, no. 12, pp. 940-951, 2016.

[8] H. Felzmann, E. Fosch-Villaronga, C. Lutz, and A. Tamò-Larrieux, “Towards transparency by design for Artificial Intelligence,” Science and Engineering Ethics, vol. 26, no. 6, pp. 3333–3361, 2020. doi:10.1007/s11948-020-00276-4

[9] V. Buhrmester, D. Münch, M. Arens, "Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey", MAKE, vol. 3, no. 4, p. 966-989, 2021. https://doi.org/10.3390/make3040048

[10] H. Tizhoosh, L. Pantanowitz, "Artificial Intelligence and Digital Pathology: Challenges and Opportunities", Journal of Pathology Informatics, vol. 9, no. 1, p. 38, 2018. https://doi.org/10.4103/jpi.jpi_53_18

[11] M. B. Muhammad and M. Yeasin, "Eigen-CAM: Class Activation Map using Principal Components," arXiv, 2020. [Online]. Available: https://doi.org/10.1109/IJCNN48605.2020.9206626.

@article{1704914,
      author = {Nevindra Ibnazhifi, Mufid Nilmada},
      title = {Interpretability to Enhance Transparency in Computer Vision System},
      journal = {Iconic Research And Engineering Journals},
      year = {2023},
      volume = {7},
      number = {1},
      pages = {541-545},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/17049141.pdf},
      abstract = {The rise of AI adoption in diverse fields has raised concerns about the transparency and accountability of decision-making processes. Computer vision companies face challenges in data transparency, bias mitigation, traceability, and AI decision explication. This research addresses these issues by investigating the implementation of explainability in computer vision systems. This study aims to provide valuable insights for improving the understanding and trustworthiness of AI models in computer vision applications by emphasizing explainability. The findings potentially foster wider acceptance of AI solutions across various industries.},
      keywords = {Computer Vision, Explainability, Transparency},
      month = {July},
  }