Abstract
In this paper, we address the problem of training a model on an image dataset that contains multiple objects that can introduce noise during the training of an image classification model. We propose a method for separating individual objects from the images and synthesizing these separated objects with a random background dataset to generate a new dataset in which each image contains a single, clearly defined object. We use the Attribution mask Compress-Semantic Input Sampling for Explanation (AC-SISE) method, a perturbation-based explainable artificial intelligence (XAI) model, to analyze the explainability of models trained on the previously generated dataset and the original dataset. The experimental results show that the ResNet50 model does not improve the explainability, but the VGG16 model improves the explainability somewhat.
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
References
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Petsiuk, V., Das, A., Saenko, K.: Rise: Randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421 (2018)
Sattarzadeh, S., et al.: Explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 13 (2021)
Kim, Y., Kim, J., Park, H.: Attribution mask Compress-SISE method for reducing the calculation volume of SISE In:. Proceedings of Symposium of the Korean Institute of communications and Information Sciences, pp. 389–390 (2023)
Everingham, M., Van, L., Williams, K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88, 303–338 (2010)
Veit, A., Wilber, M.J., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. Advances in neural information processing systems 29 (2016)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Wang, Z., Bovik, C., Sheikh, R., Simoncelli, P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Wang, H., et al.: Score-CAM: Score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 24–25 (2020)
Acknowledgments
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2022R1A2C2005705, AI-MAC Protocol on Distributed Machine Learning for Intelligent Flying Base Station).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kim, Y., Park, H. (2024). Enhancing Image Classification and Explainability with Object Isolation and Background Randomization. In: Barolli, L. (eds) Advances on P2P, Parallel, Grid, Cloud and Internet Computing . 3PGCIC 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 189. Springer, Cham. https://doi.org/10.1007/978-3-031-46970-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-46970-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46969-5
Online ISBN: 978-3-031-46970-1
eBook Packages: EngineeringEngineering (R0)